{ "data": { "a": { "slug": "fish-audio-voice-cloning", "name": "Fish Audio Voice Cloning API", "vendor": "Fish Audio", "vendorUrl": "https://fish.audio", "kind": "model", "category": "voice-cloning", "summary": "Fish Audio's API and hosted MCP server create reusable voice clones from audio samples, and the API generates candidate voices from text prompts.", "url": "https://www.anchorterminal.com/tools/fish-audio-voice-cloning", "markdownUrl": "https://www.anchorterminal.com/tools/fish-audio-voice-cloning.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/fish-audio-voice-cloning.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/fish-audio-voice-cloning.json", "dns": "fish-audio-voice-cloning.grade.anchorterminal.com", "repo": "https://github.com/fishaudio/fish-audio-python", "license": "Apache-2.0 (Python SDK)", "transports": [ "http", "streamable-http" ], "remoteUrl": "https://api.fish.audio", "packages": [ { "registry": "pypi", "name": "fish-audio-sdk" }, { "registry": "npm", "name": "fish-audio" } ], "auth": "api-key", "authNotes": "`Authorization: Bearer` API key. Voice design also needs a `model: voice-design-1` header. The hosted MCP server at `https://api.fish.audio/mcp` signs in by OAuth in the browser and is bound to one team (https://docs.fish.audio/overview/mcp).", "pricing": "usage", "pricingNotes": "Prepaid pay as you go with no subscription. No published fee for creating a voice model, and cloning on the MCP server is free. Speech from a clone costs $15 per million UTF-8 bytes on `s2.1-pro`, $50 on `drama-3` ($10 until 12 November 2026), or $0 on `s2.1-pro-free` under fair use, free through 30 November 2026 per the changelog. Voice design is $0.01 per successful request whatever the number of candidates. Concurrency rises with total prepaid spend. MCP usage draws on web app plan credits, not API credits. Separate app plans (Plus $11, Pro $75 a month, per the 30 September check) set voice slots in the web app (https://docs.fish.audio/developer-guide/models-pricing/pricing-and-rate-limits).", "priceSummary": "$0.01 / call", "where": "hosted", "x402": { "level": "no", "evidence": "No x402 or machine payment in the docs, the OpenAPI file or the pricing page (checked 2026-10-23).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 218, "npmWeekly": 6392, "pypiWeekly": 37344, "asOf": "2026-09-30" }, "docsUrl": "https://docs.fish.audio/features/voice-cloning", "llmsTxt": "https://docs.fish.audio/llms.txt", "openapi": "https://docs.fish.audio/api-reference/openapi.json", "capabilities": [ "voice.clone", "voice.design", "speech.tts" ], "tags": [ "hosted", "usage-priced", "prepaid", "python", "typescript", "openapi", "llms-txt", "open-weights", "self-hosted", "mcp" ], "lastRelease": "2026-10-30", "graded": true, "anchor": { "graded": true, "score": 61.5, "grade": "C", "agentReady": false, "rank": 604, "ranked": true, "rankOf": 1486, "categoryRank": 5, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 73, "maintenance": 72, "payments": 30, "reliability": 75, "schema": 81, "security": 35, "transparency": 61 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-04" }, "negative": 0, "verdict": "Usable clone from about 10 seconds of audio, available as soon as it's created, and an MCP server that asks the user to confirm rights before cloning. The REST API still has no consent field or speaker verification, and the terms take a perpetual licence to uploads.", "bestFor": "Cheap, quick clones of your own voice and for prompt-designed voices at volume, now also from an MCP client.", "strengths": [ "Usable clone from about 10 seconds of audio, available as soon as it's created", "Inline cloning per request, with no model to store", "`GET /model` pages and filters to your own voices with `self=true`", "Voice design at $0.01 per successful request, failed requests not billed", "S1's retirement announced 84 days ahead with a migration guide and a fallback", "Open-weights S2-Pro for self-hosting under a research licence" ], "weaknesses": [ "No consent or speaker verification on the REST API. The MCP server asks only for a rights confirmation", "Terms take a perpetual, irrevocable licence to uploads, including for training, with no opt-out", "Clones made through the MCP server are unlisted by default, usable by anyone with the ID", "npm SDK 0.1.0 (March 2026) still defaults to `s1`, deprecated on 8 October 2026", "No security.txt, SOC 2 or subprocessor list found" ], "agentNotes": [ "Send 2 or 3 clean single-speaker clips with matching `texts`, or the API runs ASR on them", "Pass the model `_id` as `reference_id` in TTS. Check `state` before relying on it", "For one-off voices send `references` inline to `/v1/tts` instead of creating a model", "List only your own voices with `GET /model?self=true`", "Send the `model: voice-design-1` header on voice design calls", "On a 429, back off exponentially. There's no `Retry-After` header, and concurrency is 5 until prepaid spend reaches $100", "On the MCP server, ask for a private voice, since `create_voice_clone` makes clones unlisted by default" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 2.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 61.5 } ], "editorialScores": { "ergonomics": 73, "maintenance": 72, "payments": 30, "reliability": 75, "schema": 81, "security": 35, "transparency": 44 }, "provenanceScore": 78, "checked": { "categories": { "ergonomics": "2026-11-04", "maintenance": "2026-11-04", "payments": "2026-11-04", "reliability": "2026-11-04", "schema": "2026-11-04", "security": "2026-11-04", "transparency": "2026-11-04" }, "last": "2026-11-04", "lastMoved": "2026-11-04", "oldest": "2026-11-04", "stale": false, "staleAfterDays": 90 } }, "connect": { "http": "curl -X POST https://api.fish.audio/model -H \"Authorization: Bearer $FISH_API_KEY\" \\\n -F type=tts -F train_mode=fast -F title=\"Support voice\" -F voices=@sample.wav", "claudeCode": "claude mcp add --transport http fish-audio https://api.fish.audio/mcp", "config": { "mcpServers": { "fish-audio": { "url": "https://api.fish.audio/mcp" } } } }, "letme": { "capability": "https://letme.dev/voice.clone", "tool": "https://letme.dev/fish-audio-voice-cloning" }, "sameCompany": [ "fish-audio-drama-3", "fish-audio-s2-pro", "fish-audio-tts" ], "area": "voice", "unitPrices": [ { "item": "Speech from a clone, s2.1-pro", "unit": "1m-chars", "usd": 15, "note": "per million UTF-8 bytes, not characters" }, { "item": "Speech from a clone, drama-3", "unit": "1m-chars", "usd": 50, "note": "per million UTF-8 bytes, $10 until 12 November 2026 09:00 PT" }, { "item": "Speech from a clone, s2.1-pro-free", "unit": "1m-chars", "usd": 0, "note": "fair-use limits, free through 30 November 2026 per the changelog" }, { "item": "Voice design, voice-design-1", "unit": "call", "usd": 0.01, "note": "per successful request, up to 4 candidates" } ], "provenance": { "legalEntity": "Hanabi AI Inc.", "domain": "fish.audio", "domainRegistered": "2023-12-11", "endpointOnVendorDomain": true, "terms": "https://fish.audio/terms/", "privacy": "https://fish.audio/privacy/", "statusPage": "https://status.fish.audio", "changelog": "https://docs.fish.audio/developer-guide/getting-started/changelog", "securityTxt": "none", "checked": "2026-11-04", "notes": [ "The Terms of Use (effective 18 August 2024) name Hanabi AI Inc. as the provider of the Services, per the 23 October check.", "The Privacy Policy is dated 28 August 2024, per the 23 October check.", "https://fish.audio/.well-known/security.txt returned 404 on 2026-10-23.", "fish.audio's Terms of Use forbid crawling, so on 4 November nothing was requested from fish.audio or its subdomains (docs, status). Every reading from those hosts is per the 23 October check, not re-read." ], "score": 78 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/fish-audio-voice-cloning.json", "live": { "slug": "fish-audio-voice-cloning", "probe": { "target": "https://api.fish.audio", "method": "get", "lastAt": "2026-11-07T18:20:25.399787632Z", "lastOk": true, "lastStatus": 404, "lastMs": 211, "authRequired": false, "uptime24h": 100, "uptime30d": 99.91, "p50ms24h": 152, "p95ms24h": 287, "samples24h": 239, "samples30d": 7910, "days": [ { "date": "2026-10-07", "probes": 272, "ok": 272 }, { "date": "2026-10-08", "probes": 268, "ok": 268 }, { "date": "2026-10-09", "probes": 250, "ok": 250 }, { "date": "2026-10-10", "probes": 247, "ok": 247 }, { "date": "2026-10-11", "probes": 247, "ok": 246 }, { "date": "2026-10-12", "probes": 247, "ok": 247 }, { "date": "2026-10-13", "probes": 248, "ok": 248 }, { "date": "2026-10-14", "probes": 249, "ok": 248 }, { "date": "2026-10-15", "probes": 253, "ok": 249 }, { "date": "2026-10-16", "probes": 252, "ok": 252 }, { "date": "2026-10-17", "probes": 253, "ok": 253 }, { "date": "2026-10-18", "probes": 256, "ok": 256 }, { "date": "2026-10-19", "probes": 255, "ok": 255 }, { "date": "2026-10-20", "probes": 252, "ok": 252 }, { "date": "2026-10-21", "probes": 253, "ok": 253 }, { "date": "2026-10-22", "probes": 253, "ok": 253 }, { "date": "2026-10-23", "probes": 248, "ok": 248 }, { "date": "2026-10-24", "probes": 251, "ok": 251 }, { "date": "2026-10-25", "probes": 250, "ok": 249 }, { "date": "2026-10-26", "probes": 252, "ok": 252 }, { "date": "2026-10-27", "probes": 249, "ok": 249 }, { "date": "2026-10-28", "probes": 251, "ok": 251 }, { "date": "2026-10-29", "probes": 248, "ok": 248 }, { "date": "2026-10-30", "probes": 249, "ok": 249 }, { "date": "2026-10-31", "probes": 251, "ok": 251 }, { "date": "2026-11-01", "probes": 249, "ok": 249 }, { "date": "2026-11-02", "probes": 250, "ok": 250 }, { "date": "2026-11-03", "probes": 248, "ok": 248 }, { "date": "2026-11-04", "probes": 246, "ok": 246 }, { "date": "2026-11-05", "probes": 185, "ok": 185 }, { "date": "2026-11-06", "probes": 241, "ok": 241 }, { "date": "2026-11-07", "probes": 187, "ok": 187 } ] }, "vendorStatus": { "page": "https://status.fish.audio", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-11-06T20:50:03.433614425Z" }, "versions": [ { "registry": "github", "name": "fishaudio/fish-audio-python", "version": "fish-audio-sdk-v1.4.0", "released": "2026-10-31", "seenAt": "2026-11-06T23:26:19.275666578Z" }, { "registry": "npm", "name": "fish-audio", "version": "0.1.0", "seenAt": "2026-11-06T23:26:19.159287784Z" }, { "registry": "pypi", "name": "fish-audio-sdk", "version": "1.4.0", "released": "2026-10-31", "seenAt": "2026-11-06T23:26:19.048257618Z" } ], "githubStars": 232, "npmWeekly": 6234, "pypiWeekly": 54219, "securityTxt": { "url": "https://fish.audio/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:01:20.344131882Z" }, "llmsTxt": { "url": "https://docs.fish.audio/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:32:32.332077471Z" }, "domain": { "domain": "fish.audio", "registered": "2023-12-11", "source": "https://rdap.centralnic.com/audio/domain/fish.audio", "checkedAt": "2026-11-01T14:23:11.45479758Z" }, "pages": [ { "url": "https://docs.fish.audio/developer-guide/getting-started/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-10-08T18:18:45.828187127Z", "changedAt": "2026-10-08T18:18:45.828187127Z", "fingerprint": "13e70b07be76" }, { "url": "https://docs.fish.audio/developer-guide/models-pricing/deprecations", "kind": "deprecations", "status": 200, "checkedAt": "2026-11-07T14:06:22.18913273Z", "changedAt": "2026-10-30T05:37:23.977055042Z", "fingerprint": "6e681f8e2daa" }, { "url": "https://docs.fish.audio/developer-guide/models-pricing/pricing-and-rate-limits", "kind": "pricing", "status": 200, "checkedAt": "2026-10-08T18:18:50.041790519Z", "changedAt": "2026-10-08T18:18:50.041790519Z", "fingerprint": "72beddda15dd" }, { "url": "https://fish.audio/privacy/", "kind": "privacy", "status": 200, "checkedAt": "2026-10-08T18:20:25.505679803Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "14953e34f56f" }, { "url": "https://fish.audio/terms/", "kind": "terms", "status": 200, "checkedAt": "2026-10-08T18:20:27.718731591Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "659fc3527722" } ], "mcpTools": { "url": "https://api.fish.audio/mcp", "checkedAt": "2026-11-07T01:44:36.579838561Z", "status": "auth", "note": "asks for credentials before listing its tools", "changedAt": "2026-11-07T01:44:36.579838561Z" }, "github": { "repo": "fishaudio/fish-audio-python", "checkedAt": "2026-11-02T08:48:46.297965397Z", "stars": 231, "archived": false, "issuesEnabled": true, "pushedAt": "2026-10-31T05:07:38Z", "openIssues": 6, "openPRs": 9, "issuesOpened90d": 0, "issuesClosed90d": 0, "prsMerged90d": 4, "ci": { "branch": "main", "runs": 50, "success": 46, "failure": 4, "other": 0, "latest": "success", "latestAt": "2026-10-31T05:04:56Z" }, "replies": { "sampled": 24, "unanswered": 5, "medianDays": 0.6 } }, "updatedAt": "2026-11-07T18:20:25.399787632Z" } }, "answer": "Inworld Instant Voice Cloning and Fish Audio Voice Cloning API score within a point of each other on agent readiness, 61.9 (C) and 61.5 (C). Fish Audio Voice Cloning API leads on schema \u0026 documentation and agent ergonomics.", "b": { "slug": "inworld-voice-cloning", "name": "Inworld Instant Voice Cloning", "vendor": "Inworld AI", "vendorUrl": "https://inworld.ai", "kind": "model", "category": "voice-cloning", "summary": "Inworld's Instant Voice Cloning API makes a reusable text-to-speech voice from 3 to 30 seconds of audio in one synchronous call, for Inworld's TTS-2 models. The same operation is in the Inworld CLI and its bundled MCP server.", "url": "https://www.anchorterminal.com/tools/inworld-voice-cloning", "markdownUrl": "https://www.anchorterminal.com/tools/inworld-voice-cloning.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/inworld-voice-cloning.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/inworld-voice-cloning.json", "dns": "inworld-voice-cloning.grade.anchorterminal.com", "repo": "https://github.com/inworld-ai/inworld-api-examples", "license": "Proprietary service under Inworld's Terms of Service. The `@inworld/cli` and `@inworld/tts` npm packages and the examples repository are MIT", "transports": [ "http", "stdio", "streamable-http" ], "remoteUrl": "https://api.inworld.ai", "packages": [ { "registry": "npm", "name": "@inworld/cli" }, { "registry": "npm", "name": "@inworld/tts" }, { "registry": "pypi", "name": "inworld-tts" } ], "auth": "api-key", "authNotes": "Self-serve workspace API key from the Portal or `inworld workspace add-key`, sent as `Authorization: Basic` with the Base64 credential as copied. Keys are read-only for the Voice API by default, and cloning, updating and deleting voices need the write toggle, which can be changed on an existing key. Deleting a key revokes it. One-time tokens minted from a key serve browser and mobile clients.", "pricing": "freemium", "pricingNotes": "Creating an instant clone has no charge in the docs or on the pricing page. Speech from a clone costs $25 per million characters on TTS-2 or $15 on TTS-2 Flash on the free On-Demand plan, falling on the $25, $100, $300 and $1,500 monthly plans. On-Demand allows 100 custom voices and 2 cloning requests a minute (checked 2026-11-06).", "priceSummary": "$25 / mo", "where": "both", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs, llms.txt or the pricing page (checked 2026-11-06). Credits are bought at a checkout page, $10 minimum.", "endpoints": [] }, "toolCount": 40, "popularity": { "githubStars": null, "npmWeekly": 3632, "pypiWeekly": null, "asOf": "2026-11-06" }, "docsUrl": "https://docs.inworld.ai/tts/instant-voice-cloning", "llmsTxt": "https://docs.inworld.ai/llms.txt", "capabilities": [ "voice.clone", "voice.design", "speech.tts" ], "tags": [ "hosted", "official", "freemium", "free-tier", "no-card", "closed-source", "python", "typescript", "llms-txt", "mcp", "cli", "status-page", "soc2" ], "lastRelease": "2026-10-29", "graded": true, "anchor": { "graded": true, "score": 61.9, "grade": "C", "agentReady": false, "rank": 585, "ranked": true, "rankOf": 1486, "categoryRank": 4, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 64, "maintenance": 68, "payments": 40, "reliability": 75, "schema": 64, "security": 55, "transparency": 63 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-06" }, "negative": 0, "verdict": "One JSON call returns a usable voice ID from 3 to 30 seconds of audio, with no charge per clone and 100 custom voices on the free plan, behind keys that are read-only until write access is switched on. The API has no consent field, and Zero Data Retention excludes cloning samples.", "bestFor": "Teams already using Inworld TTS-2 that want clones from a short clip through one call, the CLI or MCP.", "strengths": [ "Synchronous clone from 3 to 30 seconds of WAV or MP3 audio, with language auto-detection and optional background-noise removal", "No charge per clone. The free On-Demand plan includes instant cloning and 100 custom voices, and speech is $25 per million characters on TTS-2", "API keys are read-only by default. Cloning, updating and deleting voices need a write toggle that can be changed on an existing key", "`GET /voices/v1/voices` filters by `source = \"IVC\"` with paging, and `voices:customVoiceCapacity` reports how many custom voices remain", "`llms.txt`, `llms-full.txt` and a Markdown twin of every docs page, plus `clone_voice` in the MCP server in `@inworld/cli` 1.5.0 (29 October 2026)" ], "weaknesses": [ "No consent, verification or watermark field in the clone API. Only the Portal flow asks the user to confirm rights to the voice", "Zero Data Retention does not cover cloning audio samples, and no retention period for them was found", "No idempotency key on `POST /voices/v1/voices:clone`, and no error list for the Voice API", "No OpenAPI file is linked from the docs, and the repositories named in the npm metadata of the CLI and Node SDK are not public", "The MCP `clone_voice` description says about 5 seconds and 4 MB a sample, while the docs say 3 seconds and 12 MB" ], "agentNotes": [ "Create the key with write access (`inworld workspace add-key --write`). A default key gets code 7, insufficient access level, on `voices:clone`", "Send the complete Base64 credential as `Authorization: Basic $INWORLD_API_KEY`. Don't encode it again", "Send one 10 to 30 second WAV or MP3 clip as base64 in `voiceSamples[].audioData`. Audio past 30 seconds is cut", "Don't blind-retry a clone. There's no idempotency key, so list voices with `filter=source=\"IVC\"` first, and back off with jitter on 429", "Set `gender`, `ageGroup` and `categories` with UpdateVoice afterwards. The clone call ignores them without an error", "The response echoes up to 15 seconds of processed audio as base64 in `audioSamplesValidated`. Drop it before passing the result to a model" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 61.9 } ], "editorialScores": { "ergonomics": 64, "maintenance": 68, "payments": 40, "reliability": 75, "schema": 64, "security": 55, "transparency": 51 }, "provenanceScore": 75, "checked": { "categories": { "ergonomics": "2026-11-06", "maintenance": "2026-11-06", "payments": "2026-11-06", "reliability": "2026-11-06", "schema": "2026-11-06", "security": "2026-11-06", "transparency": "2026-11-06" }, "last": "2026-11-06", "oldest": "2026-11-06", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "npm install -g @inworld/cli", "http": "curl --location 'https://api.inworld.ai/voices/v1/voices:clone' \\\n --header \"Authorization: Basic $INWORLD_API_KEY\" \\\n --header 'Content-Type: application/json' \\\n --data '{\"displayName\": \"my_voice_clone_demo\", \"languageCode\": \"en-US\", \"voiceSamples\": [{\"audioData\": \"\u003cbase64-audio-data\u003e\"}]}'", "claudeCode": "claude mcp add inworld -- inworld mcp", "config": { "mcpServers": { "Inworld": { "args": [ "mcp" ], "command": "inworld" } } } }, "letme": { "capability": "https://letme.dev/voice.clone", "tool": "https://letme.dev/inworld-voice-cloning" }, "sameCompany": [ "inworld-stt", "inworld-tts", "inworld-realtime" ], "area": "voice", "unitPrices": [ { "item": "Speech from a clone, TTS-2, On-Demand", "unit": "1m-chars", "usd": 25, "note": "$20, $17.50, $15 and $12.50 on the monthly plans" }, { "item": "Speech from a clone, TTS-2 Flash, On-Demand", "unit": "1m-chars", "usd": 15, "note": "$10 down to $7 on the monthly plans" }, { "item": "Creator plan", "unit": "month", "usd": 25, "note": "credits equal to the price, 500 custom voices, 3 clone requests a minute" }, { "item": "Builder plan", "unit": "month", "usd": 100, "note": "3,000 custom voices, 5 clone requests a minute" }, { "item": "Developer plan", "unit": "month", "usd": 300, "note": "10,000 custom voices, 10 clone requests a minute" }, { "item": "Growth plan", "unit": "month", "usd": 1500, "note": "30,000 custom voices, 20 clone requests a minute" } ], "provenance": { "legalEntity": "Theai, Inc. dba Inworld AI", "domain": "inworld.ai", "domainRegistered": "", "endpointOnVendorDomain": true, "terms": "https://inworld.ai/terms", "privacy": "https://inworld.ai/privacy", "statusPage": "https://status.inworld.ai", "changelog": "https://docs.inworld.ai/release-notes/tts", "securityTxt": "none", "checked": "2026-11-06", "notes": [ "The Terms of Service (effective 11 June 2025, re-read 6 November 2026) are an agreement with Theai, Inc. dba Inworld AI under California law. They carry no clause on robots or automated access, and none specific to voice cloning.", "inworld.ai's robots.txt carries `Content-Signal: ai-train=no, search=yes, ai-input=no`, recorded as a fact about the site. Since 30 October 2026 this is not a reason to hold, so this listing, held on 9 October for it, is graded.", "status.inworld.ai draws incidents from GitHub issues in inworld-ai/inworld-issue-status, read through the GitHub API on 6 November.", "inworld.ai/.well-known/security.txt returned 404 on 30 October per the inworld-tts check. The security page links a vulnerability report form." ], "score": 75 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/inworld-voice-cloning.json", "live": { "slug": "inworld-voice-cloning", "probe": { "target": "https://api.inworld.ai", "method": "get", "lastAt": "2026-11-07T18:20:32.661612863Z", "lastOk": true, "lastStatus": 200, "lastMs": 178, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 136, "p95ms24h": 266, "samples24h": 200, "samples30d": 200, "days": [ { "date": "2026-11-06", "probes": 13, "ok": 13 }, { "date": "2026-11-07", "probes": 187, "ok": 187 } ] }, "versions": [ { "registry": "npm", "name": "@inworld/cli", "version": "1.5.0", "seenAt": "2026-11-06T23:35:10.767231519Z" }, { "registry": "npm", "name": "@inworld/tts", "version": "1.1.1", "seenAt": "2026-11-06T23:35:12.902766977Z" }, { "registry": "pypi", "name": "inworld-tts", "version": "1.2.1", "released": "2026-05-06", "seenAt": "2026-11-06T23:35:14.803764179Z" } ], "githubStars": 66, "npmWeekly": 290, "pypiWeekly": 4010, "securityTxt": { "url": "https://inworld.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:01:11.794771951Z" }, "llmsTxt": { "url": "https://docs.inworld.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:32:51.758972379Z" }, "updatedAt": "2026-11-07T18:20:32.661612863Z" } }, "edges": [ { "by": 20, "category": "security", "leads": "inworld-voice-cloning", "name": "Security \u0026 auth", "reasons": { "a": "Graded for voice cloning, with consent and misuse controls in place of the read-only line and training and retention of voice data in place of the prompt-injection line, since the API returns audio and IDs rather than third-party text. Plain revocable API keys with no scopes found. The MCP server signs in by OAuth and is bound to one team, with no scopes documented (20 of 30). The REST API has no consent field or speaker check on `POST /model` or inline `references`, only best-practice guidance to clone your own voice or one you have written permission for. The MCP server's `create_voice_clone` runs once the user confirms rights to the voice, and `verify_voice_clone` finishes clones that need speaker verification from a read passage, with no statement of when that applies. MCP clones are unlisted by default, so anyone with the ID can use them. Professional Voice Clone verification is in the web app only. No watermark or detection tool found (5 of 20). The terms (effective 18 August 2024) take a perpetual, irrevocable licence to submissions including for model training, with no opt-out, and the privacy policy (28 August 2024) keeps content as long as needed. Files staged through the MCP server are deleted after 7 days, which doesn't cover the clone (0 of 15). Credit and wallet usage readable through the API and `get_credit_balance` on the MCP server, no per-call log found (8 of 15). security.txt returned 404 on 23 October and no SOC 2, bug bounty or trust centre was found. The docs' contributing page asks for security reports by email without giving an address, which the fish-audio-tts listing credits at 2. This listing gave 0 on the same evidence, now aligned. No advisories for either SDK in OSV on 4 November (2 of 20). The pages are per the 23 October check, not re-read on 4 November. 20+5+0+8+2 = 35.", "b": "Graded for voice cloning as the other listings in this category were, with consent and misuse controls in place of the read-only line and training and retention of voice data in place of the prompt-injection line. Revocable workspace keys that are read-only for the Voice API until a write toggle is set, Realtime-only keys and single-use tokens, sent in a header (25 of 30). The API has no consent or verification field and no watermark was found. Only the Portal asks the user to confirm rights, and the Terms (11 June 2025), now read, have no clause on cloned voices. The write toggle keeps a default key from cloning (6 of 20). The Terms say Inworld won't train generally available models on non-public Materials except feedback and trust and safety content, while the Privacy Notice lists training among its uses. Zero Data Retention excludes cloning samples and no retention period for them is published (7 of 15, was 4). Usage is attributed per key in the dashboard and an experimental usage records endpoint exists from the Builder plan. No audit log found (7 of 15). GDPR and SOC 2 Type II are stated on every plan on the pricing page, and the security page links a vulnerability report form. No security.txt (404 per the 30 October inworld-tts check) and no bug bounty found (10 of 20, was 8). 25+6+7+7+10 = 55." }, "scores": { "a": 35, "b": 55 } }, { "by": 17, "category": "schema", "leads": "fish-audio-voice-cloning", "name": "Schema \u0026 documentation", "reasons": { "a": "Public OpenAPI 3.1 at docs.fish.audio/api-reference/openapi.json, re-read on 23 October with 39 paths (25). llms.txt and Markdown pages (10). The voice cloning guide says when to create a persistent model and when to pass reference audio inline (14 of 20). Inputs typed, with an enum for `visibility`, `train_mode` fixed to `fast`, 1 to 20 voice files, and ranges on every voice design field (14 of 15). Examples throughout, but the create-model reference still documents only 401 and 503 with a `{status, message, reason}` body (8 of 15). The changelog is now dated and current to 20 October 2026 and has S2.1 Pro (23 June 2026). It still has no entry for voice design or the model endpoints, and paths mix unversioned `/model` with `/v1` (10 of 15). The OpenAPI file, guides and changelog are per the 23 October check, not re-read on 4 November (fish.audio's terms forbid crawling). 25+10+14+14+8+10 = 81.", "b": "No OpenAPI file is linked from the docs or `llms.txt`, re-read on 6 November. The MCP server has typed inputs on all 40 tools, which earns part of the line (10 of 25). `llms.txt`, `llms-full.txt` and Markdown twins (10). The guides say when to use instant cloning, Professional Voice Cloning or Voice Design, and the reference warns which fields are ignored (15 of 20). Required fields and base64 audio are typed, and a new `languageCode` string is validated against the catalogue with `INVALID_ARGUMENT`, while size and length limits sit in prose and the MCP tool still states different ones (10 of 15). Examples in curl, Python, JavaScript and the CLI, with one error response shown and no error list for the Voice API (9 of 15). A `/v1/` path and dated TTS release notes, newest 11 September, with no changelog for the Voice API itself (10 of 15). 10+10+15+10+9+10 = 64." }, "scores": { "a": 81, "b": 64 } }, { "by": 10, "category": "payments", "leads": "inworld-voice-cloning", "name": "Payments \u0026 pricing", "reasons": { "a": "No x402, MPP or L402 in the docs, the OpenAPI file or the pricing page (0). Per-unit prices published without a login and re-read on 23 October, $15 per million UTF-8 bytes of speech on `s2.1-pro`, $50 on `drama-3` ($10 until 12 November 2026) and $0.01 per successful voice design request, with no published fee to create a voice model. Cloning on the MCP server is free (20). The `s2.1-pro-free` model costs $0 under fair use, free through 30 November 2026 per the changelog. The card requirement isn't stated (10 of 20). Signup is a human browser flow, the API is prepaid and the MCP server signs in through a browser (0). 0+20+10+0 = 30.", "b": "No x402, MPP or L402 (0). The pricing page, unread on 9 October and read on 6 November, publishes per-character rates for speech from a clone, $25 per million characters on TTS-2 and $15 on TTS-2 Flash on the free plan, and no charge for creating a clone (20, was 10). The On-Demand plan is free with 100 custom voices and instant cloning, and no card is asked for (20). `inworld login` opens a browser and signup is a human flow. The CLI mints keys only after that (0). 0+20+20+0 = 40." }, "scores": { "a": 30, "b": 40 } }, { "by": 9, "category": "ergonomics", "leads": "fish-audio-voice-cloning", "name": "Agent ergonomics", "reasons": { "a": "Creating a model returns the model object with author and engagement fields, heavier than an ID and status (20 of 25). `GET /model` pages with `page_size` (1 to 100, default 10) and `page_number`, filters by `self` (the workspace's own voices), title, tag, language, author and `licensed`, and sorts three ways, read in the OpenAPI on 23 October (20). Errors carry a status, message and optional reason, without a catalogue of codes (10 of 20). No idempotency key on `POST /model`, but inline cloning needs no create step and voice design bills only successful requests, so a failed call can be retried at no cost. The 429 backoff guidance doesn't change this line (10 of 20). Official Python and JavaScript SDKs and a short required field list. Python `fish-audio-sdk` 1.4.0 (30 October 2026) accepts `s2.1-pro-free` and `drama-3`, while npm `fish-audio` stays at 0.1.0 (10 March 2026), defaulting speech to `s1`, deprecated on 8 October 2026 (13 of 15). The API readings are per the 23 October check, not re-read on 4 November. 20+20+10+10+13 = 73.", "b": "The clone response echoes up to 15 seconds of processed audio as base64 with no way to leave it out. The MCP tool returns a compact result, but the server loads 40 tools with no toolsets, registering only those the credentials can call (13 of 25). Voice lists take an AIP-160 `filter`, `pageSize`, `pageToken` and `orderBy`, including `source = \"IVC\"`, and a capacity endpoint reports used and maximum custom voices (20). Errors are a numeric code, a message and details, and the one example reads clearly, but no list is documented for the Voice API (12 of 20). No idempotency key, no MCP annotations in the 1.5.0 package, and the SDKs retry 5xx and network errors twice by default (4 of 20). Two required fields, language auto-detection, and official Python and Node.js SDKs (15). 13+20+12+4+15 = 64." }, "scores": { "a": 73, "b": 64 } } ], "facts": [ { "a": "Model API", "b": "Model API", "name": "Kind" }, { "a": "Fish Audio", "b": "Inworld AI", "name": "Vendor" }, { "a": "https://api.fish.audio", "b": "https://api.inworld.ai", "name": "Hosted endpoint" }, { "a": "HTTP, Streamable HTTP", "b": "HTTP, stdio, Streamable HTTP", "name": "Transports" }, { "a": "API key", "b": "API key", "name": "Auth" }, { "a": "Pay per use", "b": "Freemium", "name": "Pricing" }, { "a": "free", "b": "$15 per 1M characters", "name": "Price for voice cloning" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache-2.0 (Python SDK)", "b": "Proprietary service under Inworld's Terms of Service. The `@inworld/cli` and `@inworld/tts` npm packages and the examples repository are MIT", "name": "Licence" }, { "a": "none", "b": "40", "name": "Tools exposed" }, { "a": "no", "b": "yes", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-30", "b": "2026-10-29", "name": "Last release" }, { "a": "2024-08-18", "b": "2025-06-11", "name": "Terms last updated" }, { "a": "2024-08-28", "b": "2026-01-18", "name": "Privacy policy last updated" }, { "a": "yes", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "yes", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "yes", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "yes", "b": "not found in the text", "name": "Arbitration or class-action waiver" }, { "a": "218 stars, 6.4k npm/wk, 37k PyPI/wk", "b": "3.6k npm/wk", "name": "Popularity" }, { "a": "2.5/5 (2)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "Inworld Instant Voice Cloning and Fish Audio Voice Cloning API score within a point of each other on agent readiness, 61.9 (C) and 61.5 (C). Fish Audio Voice Cloning API leads on schema \u0026 documentation and agent ergonomics.", "question": "Which is better for AI agents, Fish Audio Voice Cloning API or Inworld Instant Voice Cloning?" }, { "answer": "Fish Audio Voice Cloning API, at free against $15 per 1M characters for Inworld Instant Voice Cloning. These are the vendors' published prices for the job.", "question": "Which is cheaper for voice cloning, Fish Audio Voice Cloning API or Inworld Instant Voice Cloning?" }, { "answer": "Both need an API key.", "question": "Do Fish Audio Voice Cloning API and Inworld Instant Voice Cloning need an API key?" }, { "answer": "Yes. Fish Audio Voice Cloning API has a hosted endpoint at https://api.fish.audio and Inworld Instant Voice Cloning at https://api.inworld.ai.", "question": "Can an agent call Fish Audio Voice Cloning API and Inworld Instant Voice Cloning without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Schema \u0026 documentation, 81 against 64", "Agent ergonomics, 73 against 64" ], "also": [ "Cheaper for voice cloning, $0 against $15 per 1M characters" ], "goodFor": "Cheap, quick clones of your own voice and for prompt-designed voices at volume, now also from an MCP client.", "slug": "fish-audio-voice-cloning", "watchFor": "No consent or speaker verification on the REST API. The MCP server asks only for a rights confirmation" }, { "aheadOn": [ "Security \u0026 auth, 55 against 35", "Payments \u0026 pricing, 40 against 30" ], "also": [ "Runs on your own machine", "Free to start without a card" ], "goodFor": "Teams already using Inworld TTS-2 that want clones from a short clip through one call, the CLI or MCP.", "slug": "inworld-voice-cloning", "watchFor": "No consent, verification or watermark field in the clone API. Only the Portal flow asks the user to confirm rights to the voice" } ], "history": { "fish-audio-voice-cloning": [ { "causes": [ "correction" ], "date": "2026-11-04", "delta": 1.4, "from": 60.1, "fromGrade": "C", "to": 61.5, "toGrade": "C" }, { "causes": [ "evidence" ], "date": "2026-10-28", "delta": 0.1, "from": 60, "fromGrade": "C", "to": 60.1, "toGrade": "C" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.1, "from": 59.9, "fromGrade": "C", "to": 60, "toGrade": "C" } ], "inworld-voice-cloning": null }, "job": { "capability": "voice.clone", "name": "Voice cloning" }, "others": [ { "json": "https://www.anchorterminal.com/compare/cartesia-voice-cloning-vs-fish-audio-voice-cloning.json", "title": "Cartesia Voice Cloning API + MCP vs Fish Audio Voice Cloning API", "url": "https://www.anchorterminal.com/compare/cartesia-voice-cloning-vs-fish-audio-voice-cloning" }, { "json": "https://www.anchorterminal.com/compare/cartesia-voice-cloning-vs-inworld-voice-cloning.json", "title": "Cartesia Voice Cloning API + MCP vs Inworld Instant Voice Cloning", "url": "https://www.anchorterminal.com/compare/cartesia-voice-cloning-vs-inworld-voice-cloning" }, { "json": "https://www.anchorterminal.com/compare/elevenlabs-voice-cloning-vs-fish-audio-voice-cloning.json", "title": "ElevenLabs Voice Cloning and Voice Design API vs Fish Audio Voice Cloning API", "url": "https://www.anchorterminal.com/compare/elevenlabs-voice-cloning-vs-fish-audio-voice-cloning" }, { "json": "https://www.anchorterminal.com/compare/elevenlabs-voice-cloning-vs-inworld-voice-cloning.json", "title": "ElevenLabs Voice Cloning and Voice Design API vs Inworld Instant Voice Cloning", "url": "https://www.anchorterminal.com/compare/elevenlabs-voice-cloning-vs-inworld-voice-cloning" }, { "json": "https://www.anchorterminal.com/compare/fish-audio-voice-cloning-vs-gradium-voice-cloning.json", "title": "Fish Audio Voice Cloning API vs Gradium Voice Cloning and Voice Design", "url": "https://www.anchorterminal.com/compare/fish-audio-voice-cloning-vs-gradium-voice-cloning" }, { "json": "https://www.anchorterminal.com/compare/fish-audio-voice-cloning-vs-hume-voice-cloning.json", "title": "Fish Audio Voice Cloning API vs Hume Octave Voice Design and Cloning + MCP", "url": "https://www.anchorterminal.com/compare/fish-audio-voice-cloning-vs-hume-voice-cloning" }, { "json": "https://www.anchorterminal.com/compare/fish-audio-voice-cloning-vs-minimax-voice-cloning.json", "title": "Fish Audio Voice Cloning API vs MiniMax Voice Clone and Voice Design", "url": "https://www.anchorterminal.com/compare/fish-audio-voice-cloning-vs-minimax-voice-cloning" }, { "json": "https://www.anchorterminal.com/compare/fish-audio-voice-cloning-vs-murf-voice-cloning.json", "title": "Fish Audio Voice Cloning API vs Murf Voice Cloning API", "url": "https://www.anchorterminal.com/compare/fish-audio-voice-cloning-vs-murf-voice-cloning" }, { "json": "https://www.anchorterminal.com/compare/fish-audio-voice-cloning-vs-playht-voice-cloning.json", "title": "Fish Audio Voice Cloning API vs PlayHT Voice Cloning API", "url": "https://www.anchorterminal.com/compare/fish-audio-voice-cloning-vs-playht-voice-cloning" }, { "json": "https://www.anchorterminal.com/compare/fish-audio-voice-cloning-vs-resemble-ai-voice-cloning.json", "title": "Fish Audio Voice Cloning API vs Resemble AI Voice Cloning API", "url": "https://www.anchorterminal.com/compare/fish-audio-voice-cloning-vs-resemble-ai-voice-cloning" }, { "json": "https://www.anchorterminal.com/compare/fish-audio-voice-cloning-vs-smallest-voice-clone.json", "title": "Fish Audio Voice Cloning API vs Smallest.ai Instant Voice Clone", "url": "https://www.anchorterminal.com/compare/fish-audio-voice-cloning-vs-smallest-voice-clone" }, { "json": "https://www.anchorterminal.com/compare/fish-audio-voice-cloning-vs-soniox-voice-cloning.json", "title": "Fish Audio Voice Cloning API vs Soniox Voice Cloning", "url": "https://www.anchorterminal.com/compare/fish-audio-voice-cloning-vs-soniox-voice-cloning" }, { "json": "https://www.anchorterminal.com/compare/fish-audio-voice-cloning-vs-speechify-voice-cloning.json", "title": "Fish Audio Voice Cloning API vs Speechify API Voice Cloning", "url": "https://www.anchorterminal.com/compare/fish-audio-voice-cloning-vs-speechify-voice-cloning" }, { "json": "https://www.anchorterminal.com/compare/fish-audio-voice-cloning-vs-ultravox-voice-cloning.json", "title": "Fish Audio Voice Cloning API vs Ultravox Voice Cloning", "url": "https://www.anchorterminal.com/compare/fish-audio-voice-cloning-vs-ultravox-voice-cloning" }, { "json": "https://www.anchorterminal.com/compare/fish-audio-voice-cloning-vs-voicestudio.json", "title": "Fish Audio Voice Cloning API vs VoiceStudio", "url": "https://www.anchorterminal.com/compare/fish-audio-voice-cloning-vs-voicestudio" }, { "json": "https://www.anchorterminal.com/compare/gradium-voice-cloning-vs-inworld-voice-cloning.json", "title": "Gradium Voice Cloning and Voice Design vs Inworld Instant Voice Cloning", "url": "https://www.anchorterminal.com/compare/gradium-voice-cloning-vs-inworld-voice-cloning" }, { "json": "https://www.anchorterminal.com/compare/hume-voice-cloning-vs-inworld-voice-cloning.json", "title": "Hume Octave Voice Design and Cloning + MCP vs Inworld Instant Voice Cloning", "url": "https://www.anchorterminal.com/compare/hume-voice-cloning-vs-inworld-voice-cloning" }, { "json": "https://www.anchorterminal.com/compare/inworld-voice-cloning-vs-minimax-voice-cloning.json", "title": "Inworld Instant Voice Cloning vs MiniMax Voice Clone and Voice Design", "url": "https://www.anchorterminal.com/compare/inworld-voice-cloning-vs-minimax-voice-cloning" }, { "json": "https://www.anchorterminal.com/compare/inworld-voice-cloning-vs-murf-voice-cloning.json", "title": "Inworld Instant Voice Cloning vs Murf Voice Cloning API", "url": "https://www.anchorterminal.com/compare/inworld-voice-cloning-vs-murf-voice-cloning" }, { "json": "https://www.anchorterminal.com/compare/inworld-voice-cloning-vs-playht-voice-cloning.json", "title": "Inworld Instant Voice Cloning vs PlayHT Voice Cloning API", "url": "https://www.anchorterminal.com/compare/inworld-voice-cloning-vs-playht-voice-cloning" }, { "json": "https://www.anchorterminal.com/compare/inworld-voice-cloning-vs-resemble-ai-voice-cloning.json", "title": "Inworld Instant Voice Cloning vs Resemble AI Voice Cloning API", "url": "https://www.anchorterminal.com/compare/inworld-voice-cloning-vs-resemble-ai-voice-cloning" }, { "json": "https://www.anchorterminal.com/compare/inworld-voice-cloning-vs-smallest-voice-clone.json", "title": "Inworld Instant Voice Cloning vs Smallest.ai Instant Voice Clone", "url": "https://www.anchorterminal.com/compare/inworld-voice-cloning-vs-smallest-voice-clone" }, { "json": "https://www.anchorterminal.com/compare/inworld-voice-cloning-vs-soniox-voice-cloning.json", "title": "Inworld Instant Voice Cloning vs Soniox Voice Cloning", "url": "https://www.anchorterminal.com/compare/inworld-voice-cloning-vs-soniox-voice-cloning" }, { "json": "https://www.anchorterminal.com/compare/inworld-voice-cloning-vs-speechify-voice-cloning.json", "title": "Inworld Instant Voice Cloning vs Speechify API Voice Cloning", "url": "https://www.anchorterminal.com/compare/inworld-voice-cloning-vs-speechify-voice-cloning" }, { "json": "https://www.anchorterminal.com/compare/inworld-voice-cloning-vs-ultravox-voice-cloning.json", "title": "Inworld Instant Voice Cloning vs Ultravox Voice Cloning", "url": "https://www.anchorterminal.com/compare/inworld-voice-cloning-vs-ultravox-voice-cloning" }, { "json": "https://www.anchorterminal.com/compare/inworld-voice-cloning-vs-voicestudio.json", "title": "Inworld Instant Voice Cloning vs VoiceStudio", "url": "https://www.anchorterminal.com/compare/inworld-voice-cloning-vs-voicestudio" } ], "panel": null, "scores": [ { "by": 0, "edge": "", "fish-audio-voice-cloning": 75, "inworld-voice-cloning": 75, "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 17, "edge": "fish-audio-voice-cloning", "fish-audio-voice-cloning": 81, "inworld-voice-cloning": 64, "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 9, "edge": "fish-audio-voice-cloning", "fish-audio-voice-cloning": 73, "inworld-voice-cloning": 64, "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "by": 20, "edge": "inworld-voice-cloning", "fish-audio-voice-cloning": 35, "inworld-voice-cloning": 55, "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "by": 10, "edge": "inworld-voice-cloning", "fish-audio-voice-cloning": 30, "inworld-voice-cloning": 40, "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 4, "edge": "fish-audio-voice-cloning", "fish-audio-voice-cloning": 72, "inworld-voice-cloning": 68, "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 2, "edge": "inworld-voice-cloning", "fish-audio-voice-cloning": 61, "inworld-voice-cloning": 63, "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Inworld Instant Voice Cloning and Fish Audio Voice Cloning API score within a point of each other on agent readiness, 61.9 (C) and 61.5 (C). Fish Audio Voice Cloning API leads on schema \u0026 documentation and agent ergonomics. Both do voice cloning. Fish Audio Voice Cloning API is cheaper for voice cloning, $0 against $15 per 1M characters.", "tasks": [ { "a": "$0.13 to $0.45", "b": "$0.13 to $0.22", "cheaper": "", "task": "Narrate a 9,000-character script", "what": "about 1,500 words" } ], "tutorials": [ { "title": "Create a private voice model with Fish Audio", "tool": "fish-audio-voice-cloning", "url": "https://www.anchorterminal.com/tutorials/fish-audio-voice-cloning/" } ], "verdicts": { "fish-audio-voice-cloning": "Usable clone from about 10 seconds of audio, available as soon as it's created, and an MCP server that asks the user to confirm rights before cloning. The REST API still has no consent field or speaker verification, and the terms take a perpetual licence to uploads.", "inworld-voice-cloning": "One JSON call returns a usable voice ID from 3 to 30 seconds of audio, with no charge per clone and 100 custom voices on the free plan, behind keys that are read-only until write access is switched on. The API has no consent field, and Zero Data Retention excludes cloning samples." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/fish-audio-voice-cloning-vs-inworld-voice-cloning", "json": "https://www.anchorterminal.com/compare/fish-audio-voice-cloning-vs-inworld-voice-cloning.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/fish-audio-voice-cloning-vs-inworld-voice-cloning.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/fish-audio-voice-cloning-vs-inworld-voice-cloning.min.md" }, "markdown": "Inworld Instant Voice Cloning and Fish Audio Voice Cloning API score within a point of each other on agent readiness, 61.9 (C) and 61.5 (C). Fish Audio Voice Cloning API leads on schema \u0026 documentation and agent ergonomics. Both do voice cloning. Fish Audio Voice Cloning API is cheaper for voice cloning, $0 against $15 per 1M characters.\n\n- Fish Audio Voice Cloning API: grade C, 61.5/100, rank #604 of 1486. Markdown https://www.anchorterminal.com/tools/fish-audio-voice-cloning.md · JSON https://www.anchorterminal.com/api/v1/tools/fish-audio-voice-cloning.json\n- Inworld Instant Voice Cloning: grade C, 61.9/100, rank #585 of 1486. Markdown https://www.anchorterminal.com/tools/inworld-voice-cloning.md · JSON https://www.anchorterminal.com/api/v1/tools/inworld-voice-cloning.json\n- Best voice cloning and custom voice APIs for AI agents: https://www.anchorterminal.com/best/voice-cloning/index.md\n- All 133 cloning comparisons: https://www.anchorterminal.com/compare/voice-cloning/index.md\n\n## Which one, for what\n\n### Fish Audio Voice Cloning API (C)\n\nGood for: Cheap, quick clones of your own voice and for prompt-designed voices at volume, now also from an MCP client.\n\nAhead on:\n- Schema \u0026 documentation, 81 against 64\n- Agent ergonomics, 73 against 64\n\nAlso in its favour:\n- Cheaper for voice cloning, $0 against $15 per 1M characters\n\nWatch for: No consent or speaker verification on the REST API. The MCP server asks only for a rights confirmation\n\n### Inworld Instant Voice Cloning (C)\n\nGood for: Teams already using Inworld TTS-2 that want clones from a short clip through one call, the CLI or MCP.\n\nAhead on:\n- Security \u0026 auth, 55 against 35\n- Payments \u0026 pricing, 40 against 30\n\nAlso in its favour:\n- Runs on your own machine\n- Free to start without a card\n\nWatch for: No consent, verification or watermark field in the clone API. Only the Portal flow asks the user to confirm rights to the voice\n\n\n## Why the edge\n\n### Security \u0026 auth: Inworld Instant Voice Cloning +20\n\n- Fish Audio Voice Cloning API (35): Graded for voice cloning, with consent and misuse controls in place of the read-only line and training and retention of voice data in place of the prompt-injection line, since the API returns audio and IDs rather than third-party text. Plain revocable API keys with no scopes found. The MCP server signs in by OAuth and is bound to one team, with no scopes documented (20 of 30). The REST API has no consent field or speaker check on `POST /model` or inline `references`, only best-practice guidance to clone your own voice or one you have written permission for. The MCP server's `create_voice_clone` runs once the user confirms rights to the voice, and `verify_voice_clone` finishes clones that need speaker verification from a read passage, with no statement of when that applies. MCP clones are unlisted by default, so anyone with the ID can use them. Professional Voice Clone verification is in the web app only. No watermark or detection tool found (5 of 20). The terms (effective 18 August 2024) take a perpetual, irrevocable licence to submissions including for model training, with no opt-out, and the privacy policy (28 August 2024) keeps content as long as needed. Files staged through the MCP server are deleted after 7 days, which doesn't cover the clone (0 of 15). Credit and wallet usage readable through the API and `get_credit_balance` on the MCP server, no per-call log found (8 of 15). security.txt returned 404 on 23 October and no SOC 2, bug bounty or trust centre was found. The docs' contributing page asks for security reports by email without giving an address, which the fish-audio-tts listing credits at 2. This listing gave 0 on the same evidence, now aligned. No advisories for either SDK in OSV on 4 November (2 of 20). The pages are per the 23 October check, not re-read on 4 November. 20+5+0+8+2 = 35.\n- Inworld Instant Voice Cloning (55): Graded for voice cloning as the other listings in this category were, with consent and misuse controls in place of the read-only line and training and retention of voice data in place of the prompt-injection line. Revocable workspace keys that are read-only for the Voice API until a write toggle is set, Realtime-only keys and single-use tokens, sent in a header (25 of 30). The API has no consent or verification field and no watermark was found. Only the Portal asks the user to confirm rights, and the Terms (11 June 2025), now read, have no clause on cloned voices. The write toggle keeps a default key from cloning (6 of 20). The Terms say Inworld won't train generally available models on non-public Materials except feedback and trust and safety content, while the Privacy Notice lists training among its uses. Zero Data Retention excludes cloning samples and no retention period for them is published (7 of 15, was 4). Usage is attributed per key in the dashboard and an experimental usage records endpoint exists from the Builder plan. No audit log found (7 of 15). GDPR and SOC 2 Type II are stated on every plan on the pricing page, and the security page links a vulnerability report form. No security.txt (404 per the 30 October inworld-tts check) and no bug bounty found (10 of 20, was 8). 25+6+7+7+10 = 55.\n\n### Schema \u0026 documentation: Fish Audio Voice Cloning API +17\n\n- Fish Audio Voice Cloning API (81): Public OpenAPI 3.1 at docs.fish.audio/api-reference/openapi.json, re-read on 23 October with 39 paths (25). llms.txt and Markdown pages (10). The voice cloning guide says when to create a persistent model and when to pass reference audio inline (14 of 20). Inputs typed, with an enum for `visibility`, `train_mode` fixed to `fast`, 1 to 20 voice files, and ranges on every voice design field (14 of 15). Examples throughout, but the create-model reference still documents only 401 and 503 with a `{status, message, reason}` body (8 of 15). The changelog is now dated and current to 20 October 2026 and has S2.1 Pro (23 June 2026). It still has no entry for voice design or the model endpoints, and paths mix unversioned `/model` with `/v1` (10 of 15). The OpenAPI file, guides and changelog are per the 23 October check, not re-read on 4 November (fish.audio's terms forbid crawling). 25+10+14+14+8+10 = 81.\n- Inworld Instant Voice Cloning (64): No OpenAPI file is linked from the docs or `llms.txt`, re-read on 6 November. The MCP server has typed inputs on all 40 tools, which earns part of the line (10 of 25). `llms.txt`, `llms-full.txt` and Markdown twins (10). The guides say when to use instant cloning, Professional Voice Cloning or Voice Design, and the reference warns which fields are ignored (15 of 20). Required fields and base64 audio are typed, and a new `languageCode` string is validated against the catalogue with `INVALID_ARGUMENT`, while size and length limits sit in prose and the MCP tool still states different ones (10 of 15). Examples in curl, Python, JavaScript and the CLI, with one error response shown and no error list for the Voice API (9 of 15). A `/v1/` path and dated TTS release notes, newest 11 September, with no changelog for the Voice API itself (10 of 15). 10+10+15+10+9+10 = 64.\n\n### Payments \u0026 pricing: Inworld Instant Voice Cloning +10\n\n- Fish Audio Voice Cloning API (30): No x402, MPP or L402 in the docs, the OpenAPI file or the pricing page (0). Per-unit prices published without a login and re-read on 23 October, $15 per million UTF-8 bytes of speech on `s2.1-pro`, $50 on `drama-3` ($10 until 12 November 2026) and $0.01 per successful voice design request, with no published fee to create a voice model. Cloning on the MCP server is free (20). The `s2.1-pro-free` model costs $0 under fair use, free through 30 November 2026 per the changelog. The card requirement isn't stated (10 of 20). Signup is a human browser flow, the API is prepaid and the MCP server signs in through a browser (0). 0+20+10+0 = 30.\n- Inworld Instant Voice Cloning (40): No x402, MPP or L402 (0). The pricing page, unread on 9 October and read on 6 November, publishes per-character rates for speech from a clone, $25 per million characters on TTS-2 and $15 on TTS-2 Flash on the free plan, and no charge for creating a clone (20, was 10). The On-Demand plan is free with 100 custom voices and instant cloning, and no card is asked for (20). `inworld login` opens a browser and signup is a human flow. The CLI mints keys only after that (0). 0+20+20+0 = 40.\n\n### Agent ergonomics: Fish Audio Voice Cloning API +9\n\n- Fish Audio Voice Cloning API (73): Creating a model returns the model object with author and engagement fields, heavier than an ID and status (20 of 25). `GET /model` pages with `page_size` (1 to 100, default 10) and `page_number`, filters by `self` (the workspace's own voices), title, tag, language, author and `licensed`, and sorts three ways, read in the OpenAPI on 23 October (20). Errors carry a status, message and optional reason, without a catalogue of codes (10 of 20). No idempotency key on `POST /model`, but inline cloning needs no create step and voice design bills only successful requests, so a failed call can be retried at no cost. The 429 backoff guidance doesn't change this line (10 of 20). Official Python and JavaScript SDKs and a short required field list. Python `fish-audio-sdk` 1.4.0 (30 October 2026) accepts `s2.1-pro-free` and `drama-3`, while npm `fish-audio` stays at 0.1.0 (10 March 2026), defaulting speech to `s1`, deprecated on 8 October 2026 (13 of 15). The API readings are per the 23 October check, not re-read on 4 November. 20+20+10+10+13 = 73.\n- Inworld Instant Voice Cloning (64): The clone response echoes up to 15 seconds of processed audio as base64 with no way to leave it out. The MCP tool returns a compact result, but the server loads 40 tools with no toolsets, registering only those the credentials can call (13 of 25). Voice lists take an AIP-160 `filter`, `pageSize`, `pageToken` and `orderBy`, including `source = \"IVC\"`, and a capacity endpoint reports used and maximum custom voices (20). Errors are a numeric code, a message and details, and the one example reads clearly, but no list is documented for the Voice API (12 of 20). No idempotency key, no MCP annotations in the 1.5.0 package, and the SDKs retry 5xx and network errors twice by default (4 of 20). Two required fields, language auto-detection, and official Python and Node.js SDKs (15). 13+20+12+4+15 = 64.\n\n## Score by category\n\n| Category | Weight | Fish Audio Voice Cloning API | Inworld Instant Voice Cloning | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 75 | 75 | even |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 81 | 64 | Fish Audio Voice Cloning API +17 |\n| Agent ergonomics | 13% (16.2 this run) | 73 | 64 | Fish Audio Voice Cloning API +9 |\n| Security \u0026 auth | 14% (17.5 this run) | 35 | 55 | Inworld Instant Voice Cloning +20 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 30 | 40 | Inworld Instant Voice Cloning +10 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 72 | 68 | Fish Audio Voice Cloning API +4 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 61 | 63 | Inworld Instant Voice Cloning +2 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **61.5 · C** | **61.9 · C** | |\n\n## Facts side by side\n\n| Fact | Fish Audio Voice Cloning API | Inworld Instant Voice Cloning |\n| --- | --- | --- |\n| Kind | Model API | Model API |\n| Vendor | Fish Audio | Inworld AI |\n| Hosted endpoint | `https://api.fish.audio` | `https://api.inworld.ai` |\n| Transports | HTTP, Streamable HTTP | HTTP, stdio, Streamable HTTP |\n| Auth | API key | API key |\n| Pricing | Pay per use | Freemium |\n| Price for voice cloning | free | $15 per 1M characters |\n| x402 | no | no |\n| Licence | Apache-2.0 (Python SDK) | Proprietary service under Inworld's Terms of Service. The `@inworld/cli` and `@inworld/tts` npm packages and the examples repository are MIT |\n| Tools exposed | none | 40 |\n| Read-only variant documented | no | yes |\n| llms.txt | yes | yes |\n| Last release | 2026-10-30 | 2026-10-29 |\n| Terms last updated | 2024-08-18 | 2025-06-11 |\n| Privacy policy last updated | 2024-08-28 | 2026-01-18 |\n| Customer content may train models | yes | not found in the text |\n| Terms restrict automated access | yes | not found in the text |\n| Terms restrict benchmarking | yes | not found in the text |\n| Terms or service can change without notice | not found in the text | not found in the text |\n| Arbitration or class-action waiver | yes | not found in the text |\n| Popularity | 218 stars, 6.4k npm/wk, 37k PyPI/wk | 3.6k npm/wk |\n| Agent reviews | 2.5/5 (2) | none |\n\n## What the same task costs\n\n| Task | Fish Audio Voice Cloning API | Inworld Instant Voice Cloning |\n| --- | --- | --- |\n| Narrate a 9,000-character script | $0.13 to $0.45 | $0.13 to $0.22 |\n\n## How the scores have moved\n\n### Fish Audio Voice Cloning API\n\n- +1.4 on 4 November 2026: correction\n- +0.1 on 28 October 2026: new evidence\n- +0.1 on 27 October 2026: checklist\n\n### Inworld Instant Voice Cloning\n\nNo score change since it was listed.\n\n## Verdicts\n\n**Fish Audio Voice Cloning API.** Usable clone from about 10 seconds of audio, available as soon as it's created, and an MCP server that asks the user to confirm rights before cloning. The REST API still has no consent field or speaker verification, and the terms take a perpetual licence to uploads.\n\n**Inworld Instant Voice Cloning.** One JSON call returns a usable voice ID from 3 to 30 seconds of audio, with no charge per clone and 100 custom voices on the free plan, behind keys that are read-only until write access is switched on. The API has no consent field, and Zero Data Retention excludes cloning samples.\n\n## Before you call either\n\n### Fish Audio Voice Cloning API\n\n1. Send 2 or 3 clean single-speaker clips with matching `texts`, or the API runs ASR on them\n2. Pass the model `_id` as `reference_id` in TTS. Check `state` before relying on it\n3. For one-off voices send `references` inline to `/v1/tts` instead of creating a model\n4. List only your own voices with `GET /model?self=true`\n5. Send the `model: voice-design-1` header on voice design calls\n6. On a 429, back off exponentially. There's no `Retry-After` header, and concurrency is 5 until prepaid spend reaches $100\n7. On the MCP server, ask for a private voice, since `create_voice_clone` makes clones unlisted by default\n\n### Inworld Instant Voice Cloning\n\n1. Create the key with write access (`inworld workspace add-key --write`). A default key gets code 7, insufficient access level, on `voices:clone`\n2. Send the complete Base64 credential as `Authorization: Basic $INWORLD_API_KEY`. Don't encode it again\n3. Send one 10 to 30 second WAV or MP3 clip as base64 in `voiceSamples[].audioData`. Audio past 30 seconds is cut\n4. Don't blind-retry a clone. There's no idempotency key, so list voices with `filter=source=\"IVC\"` first, and back off with jitter on 429\n5. Set `gender`, `ageGroup` and `categories` with UpdateVoice afterwards. The clone call ignores them without an error\n6. The response echoes up to 15 seconds of processed audio as base64 in `audioSamplesValidated`. Drop it before passing the result to a model\n\n## Tutorials\n\n- [Create a private voice model with Fish Audio](https://www.anchorterminal.com/tutorials/fish-audio-voice-cloning/), for Fish Audio Voice Cloning API\n\n## Questions\n\n### Which is better for AI agents, Fish Audio Voice Cloning API or Inworld Instant Voice Cloning?\n\nInworld Instant Voice Cloning and Fish Audio Voice Cloning API score within a point of each other on agent readiness, 61.9 (C) and 61.5 (C). Fish Audio Voice Cloning API leads on schema \u0026 documentation and agent ergonomics.\n\n### Which is cheaper for voice cloning, Fish Audio Voice Cloning API or Inworld Instant Voice Cloning?\n\nFish Audio Voice Cloning API, at free against $15 per 1M characters for Inworld Instant Voice Cloning. These are the vendors' published prices for the job.\n\n### Do Fish Audio Voice Cloning API and Inworld Instant Voice Cloning need an API key?\n\nBoth need an API key.\n\n### Can an agent call Fish Audio Voice Cloning API and Inworld Instant Voice Cloning without installing anything?\n\nYes. Fish Audio Voice Cloning API has a hosted endpoint at https://api.fish.audio and Inworld Instant Voice Cloning at https://api.inworld.ai.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/fish-audio-voice-cloning-vs-inworld-voice-cloning.json, and with the fewest tokens: https://www.anchorterminal.com/compare/fish-audio-voice-cloning-vs-inworld-voice-cloning.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"fish-audio-voice-cloning\", \"b\": \"inworld-voice-cloning\"}`. From a terminal: `anchor compare fish-audio-voice-cloning inworld-voice-cloning`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/fish-audio-voice-cloning.json and https://www.anchorterminal.com/api/v1/tools/inworld-voice-cloning.json\n\n## Other comparisons with Fish Audio Voice Cloning API or Inworld Instant Voice Cloning\n\n- [Cartesia Voice Cloning API + MCP vs Fish Audio Voice Cloning API](https://www.anchorterminal.com/compare/cartesia-voice-cloning-vs-fish-audio-voice-cloning.md)\n- [Cartesia Voice Cloning API + MCP vs Inworld Instant Voice Cloning](https://www.anchorterminal.com/compare/cartesia-voice-cloning-vs-inworld-voice-cloning.md)\n- [ElevenLabs Voice Cloning and Voice Design API vs Fish Audio Voice Cloning API](https://www.anchorterminal.com/compare/elevenlabs-voice-cloning-vs-fish-audio-voice-cloning.md)\n- [ElevenLabs Voice Cloning and Voice Design API vs Inworld Instant Voice Cloning](https://www.anchorterminal.com/compare/elevenlabs-voice-cloning-vs-inworld-voice-cloning.md)\n- [Fish Audio Voice Cloning API vs Gradium Voice Cloning and Voice Design](https://www.anchorterminal.com/compare/fish-audio-voice-cloning-vs-gradium-voice-cloning.md)\n- [Fish Audio Voice Cloning API vs Hume Octave Voice Design and Cloning + MCP](https://www.anchorterminal.com/compare/fish-audio-voice-cloning-vs-hume-voice-cloning.md)\n- [Fish Audio Voice Cloning API vs MiniMax Voice Clone and Voice Design](https://www.anchorterminal.com/compare/fish-audio-voice-cloning-vs-minimax-voice-cloning.md)\n- [Fish Audio Voice Cloning API vs Murf Voice Cloning API](https://www.anchorterminal.com/compare/fish-audio-voice-cloning-vs-murf-voice-cloning.md)\n- [Fish Audio Voice Cloning API vs PlayHT Voice Cloning API](https://www.anchorterminal.com/compare/fish-audio-voice-cloning-vs-playht-voice-cloning.md)\n- [Fish Audio Voice Cloning API vs Resemble AI Voice Cloning API](https://www.anchorterminal.com/compare/fish-audio-voice-cloning-vs-resemble-ai-voice-cloning.md)\n- [Fish Audio Voice Cloning API vs Smallest.ai Instant Voice Clone](https://www.anchorterminal.com/compare/fish-audio-voice-cloning-vs-smallest-voice-clone.md)\n- [Fish Audio Voice Cloning API vs Soniox Voice Cloning](https://www.anchorterminal.com/compare/fish-audio-voice-cloning-vs-soniox-voice-cloning.md)\n- [Fish Audio Voice Cloning API vs Speechify API Voice Cloning](https://www.anchorterminal.com/compare/fish-audio-voice-cloning-vs-speechify-voice-cloning.md)\n- [Fish Audio Voice Cloning API vs Ultravox Voice Cloning](https://www.anchorterminal.com/compare/fish-audio-voice-cloning-vs-ultravox-voice-cloning.md)\n- [Fish Audio Voice Cloning API vs VoiceStudio](https://www.anchorterminal.com/compare/fish-audio-voice-cloning-vs-voicestudio.md)\n- [Gradium Voice Cloning and Voice Design vs Inworld Instant Voice Cloning](https://www.anchorterminal.com/compare/gradium-voice-cloning-vs-inworld-voice-cloning.md)\n- [Hume Octave Voice Design and Cloning + MCP vs Inworld Instant Voice Cloning](https://www.anchorterminal.com/compare/hume-voice-cloning-vs-inworld-voice-cloning.md)\n- [Inworld Instant Voice Cloning vs MiniMax Voice Clone and Voice Design](https://www.anchorterminal.com/compare/inworld-voice-cloning-vs-minimax-voice-cloning.md)\n- [Inworld Instant Voice Cloning vs Murf Voice Cloning API](https://www.anchorterminal.com/compare/inworld-voice-cloning-vs-murf-voice-cloning.md)\n- [Inworld Instant Voice Cloning vs PlayHT Voice Cloning API](https://www.anchorterminal.com/compare/inworld-voice-cloning-vs-playht-voice-cloning.md)\n- [Inworld Instant Voice Cloning vs Resemble AI Voice Cloning API](https://www.anchorterminal.com/compare/inworld-voice-cloning-vs-resemble-ai-voice-cloning.md)\n- [Inworld Instant Voice Cloning vs Smallest.ai Instant Voice Clone](https://www.anchorterminal.com/compare/inworld-voice-cloning-vs-smallest-voice-clone.md)\n- [Inworld Instant Voice Cloning vs Soniox Voice Cloning](https://www.anchorterminal.com/compare/inworld-voice-cloning-vs-soniox-voice-cloning.md)\n- [Inworld Instant Voice Cloning vs Speechify API Voice Cloning](https://www.anchorterminal.com/compare/inworld-voice-cloning-vs-speechify-voice-cloning.md)\n- [Inworld Instant Voice Cloning vs Ultravox Voice Cloning](https://www.anchorterminal.com/compare/inworld-voice-cloning-vs-ultravox-voice-cloning.md)\n- [Inworld Instant Voice Cloning vs VoiceStudio](https://www.anchorterminal.com/compare/inworld-voice-cloning-vs-voicestudio.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-07", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Fish Audio Voice Cloning API vs Inworld Instant Voice Cloning", "url": "" } ], "description": "Inworld Instant Voice Cloning and Fish Audio Voice Cloning score within a point of each other for voice cloning, 61.9 and 61.5 out of 100. Fish Audio Voice Cloning is cheaper for voice cloning, $0 against $15 per 1M characters. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Fish Audio Voice Cloning API C 61.5", "Inworld Instant Voice Cloning C 61.9", "scores" ], "h1": "Fish Audio Voice Cloning API vs Inworld Instant Voice Cloning", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/fish-audio-voice-cloning-vs-inworld-voice-cloning", "published": "2026-10-01", "section": "tools", "title": "Fish Audio Voice Cloning vs Inworld Instant Voice Cloning (2026)", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/fish-audio-voice-cloning-vs-inworld-voice-cloning" }, "tokens": { "markdown": 5500, "slim": 2930 }, "version": 1 }