{ "data": { "a": { "slug": "deepgram-tts", "name": "Deepgram Text-to-Speech (Aura-2, Flux TTS)", "vendor": "Deepgram", "vendorUrl": "https://deepgram.com", "kind": "model", "category": "text-to-speech", "summary": "Deepgram's text-to-speech API for generating spoken audio.", "url": "https://www.anchorterminal.com/tools/deepgram-tts", "markdownUrl": "https://www.anchorterminal.com/tools/deepgram-tts.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/deepgram-tts.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/deepgram-tts.json", "repo": "https://github.com/deepgram/deepgram-python-sdk", "license": "MIT (SDKs)", "transports": [ "http", "streamable-http", "stdio", "sse" ], "remoteUrl": "https://api.deepgram.com/v1", "packages": [ { "registry": "npm", "name": "@deepgram/sdk" }, { "registry": "pypi", "name": "deepgram-sdk" }, { "registry": "pypi", "name": "deepctl" } ], "auth": "api-key", "authNotes": "`Authorization: Token \u003ckey\u003e` header on REST and WebSocket calls. Short-lived JWTs (30-second TTL) from the token endpoint for browsers. The `dg` CLI MCP server uses `dg login` credentials or `DEEPGRAM_API_KEY`. The docs MCP needs no key.", "pricing": "usage", "pricingNotes": "$200 free credit with no card, then pay as you go. Flux TTS $0.045 per 1,000 characters, Aura-2 $0.030, Aura-1 $0.015. Growth (from $4,000 a year prepaid) cuts these to $0.0405, $0.027 and $0.0135. A matching-credit offer on Flux TTS runs to 2026-12-31, capped at $500 (https://deepgram.com/pricing).", "priceSummary": "Pay per use", "where": "both", "x402": { "level": "no", "evidence": "No x402 or machine payment in the docs or pricing. Card or prepaid credits only (checked 2026-09-30).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 468, "npmWeekly": 1123798, "pypiWeekly": 805026, "asOf": "2026-09-30" }, "docsUrl": "https://developers.deepgram.com/docs/tts-models-languages-overview", "llmsTxt": "https://developers.deepgram.com/llms.txt", "openapi": "https://developers.deepgram.com/openapi.json", "capabilities": [ "speech.tts", "speech.streaming", "speech.voices", "speech.languages" ], "tags": [ "hosted", "no-card", "closed-source", "python", "typescript", "openapi", "llms-txt", "mcp", "streaming", "batch", "enterprise", "self-hosted" ], "lastRelease": "2026-09-29", "graded": true, "anchor": { "graded": true, "score": 72.7, "grade": "BB", "agentReady": true, "rank": 97, "ranked": true, "rankOf": 842, "categoryRank": 3, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 82, "maintenance": 73, "payments": 40, "reliability": 70, "schema": 95, "security": 70, "transparency": 72 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "high", "date": "2026-10-01" }, "negative": 0, "verdict": "OpenAPI 3.1 and AsyncAPI files, llms.txt and Markdown pages. Requests can be kept for training unless each one sets `mip_opt_out=true`.", "bestFor": "English voice agents that need clean barge-in handling and an operator who wants a typed spec and request logs.", "strengths": [ "OpenAPI 3.1 and AsyncAPI files, llms.txt and Markdown pages", "Flux TTS's Interrupt event returns `text_spoken` and `text_remaining` on barge-in", "Keys carry roles and scopes, and browser tokens live 30 seconds", "Per-request logs through `GET /v1/projects/{project_id}/requests`, filterable by date and status", "$200 credit with no card, then Aura-2 at $0.030 per 1,000 characters" ], "weaknesses": [ "Requests can be kept for training unless each one sets `mip_opt_out=true`", "Flux TTS is English only and capped at 5 concurrent streams in the EU, Australia and India below Enterprise", "No SSML, and Flux TTS strips other vendors' tags with a warning", "Elevated Flux TTS errors for about four hours on 25 September 2026", "Aura-2 REST requests stop at 2,000 characters" ], "agentNotes": [ "Set `mip_opt_out=true` on every request if the text mustn't be kept for training.", "Split Aura-2 REST text under 2,000 characters or expect a 413.", "Pass `model` on `/v2/speak`, where it's required.", "Strip SSML before sending, since it's removed with an `INPUT_MARKUP_STRIPPED` warning.", "Back off exponentially on 429 and keep traffic in one project." ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 3.5, "history": [ { "basis": "public evidence", "confidence": "high", "grade": "BB", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 72.7 } ], "editorialScores": { "ergonomics": 82, "maintenance": 73, "payments": 40, "reliability": 70, "schema": 95, "security": 70, "transparency": 60 }, "provenanceScore": 84 }, "connect": { "http": "curl \"https://api.deepgram.com/v1/speak?model=aura-2-thalia-en\" \\\n -H \"Authorization: Token $DEEPGRAM_API_KEY\" -H \"content-type: application/json\" \\\n -d '{\"text\":\"Hello, how are you?\"}' -o hello.mp3", "claudeCode": "claude mcp add deepgram-docs --transport http https://api.dx.deepgram.com/kapa/mcp", "config": { "mcpServers": { "deepgram": { "args": [ "mcp" ], "command": "dg", "env": { "DEEPGRAM_API_KEY": "${DEEPGRAM_API_KEY}" } } } } }, "letme": { "capability": "https://letme.dev/speech.tts", "tool": "https://letme.dev/deepgram-tts" }, "sameCompany": [ "deepgram-stt", "deepgram-voice-agent" ], "area": "voice", "unitPrices": [ { "item": "Flux TTS", "unit": "1m-chars", "usd": 45, "note": "pay as you go, $0.045 per 1,000 characters" }, { "item": "Aura-2", "unit": "1m-chars", "usd": 30, "note": "pay as you go" }, { "item": "Aura-1", "unit": "1m-chars", "usd": 15, "note": "pay as you go" }, { "item": "Aura-2 on Growth", "unit": "1m-chars", "usd": 27, "note": "prepaid annual plan from $4,000" } ], "provenance": { "legalEntity": "Deepgram, Inc.", "domain": "deepgram.com", "domainRegistered": "2016-01-28", "endpointOnVendorDomain": true, "terms": "https://deepgram.com/terms", "privacy": "https://deepgram.com/privacy", "statusPage": "https://status.deepgram.com", "changelog": "https://developers.deepgram.com/changelog", "securityTxt": "none", "checked": "2026-09-30", "score": 84 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/deepgram-tts.json", "live": { "slug": "deepgram-tts", "probe": { "target": "https://api.deepgram.com/v1", "method": "get", "lastAt": "2026-10-09T10:42:41.15295706Z", "lastOk": true, "lastStatus": 404, "lastMs": 408, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 372, "p95ms24h": 489, "samples24h": 260, "samples30d": 2300, "days": [ { "date": "2026-09-30", "probes": 35, "ok": 35 }, { "date": "2026-10-01", "probes": 276, "ok": 276 }, { "date": "2026-10-02", "probes": 248, "ok": 248 }, { "date": "2026-10-03", "probes": 271, "ok": 271 }, { "date": "2026-10-04", "probes": 272, "ok": 272 }, { "date": "2026-10-05", "probes": 272, "ok": 272 }, { "date": "2026-10-06", "probes": 272, "ok": 272 }, { "date": "2026-10-07", "probes": 272, "ok": 272 }, { "date": "2026-10-08", "probes": 268, "ok": 268 }, { "date": "2026-10-09", "probes": 114, "ok": 114 } ] }, "vendorStatus": { "page": "https://status.deepgram.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-10-09T10:41:33.167771924Z" }, "versions": [ { "registry": "github", "name": "deepgram/deepgram-python-sdk", "version": "v7.12.0", "released": "2026-10-02", "seenAt": "2026-10-08T16:08:20.923005026Z" }, { "registry": "npm", "name": "@deepgram/sdk", "version": "5.14.0", "seenAt": "2026-10-08T16:08:15.453210633Z" }, { "registry": "pypi", "name": "deepctl", "version": "0.3.2", "released": "2026-10-05", "seenAt": "2026-10-08T16:08:19.033633404Z" }, { "registry": "pypi", "name": "deepgram-sdk", "version": "7.12.0", "released": "2026-10-02", "seenAt": "2026-10-08T16:08:18.915263004Z" } ], "githubStars": 469, "npmWeekly": 1133092, "pypiWeekly": 784290, "securityTxt": { "url": "https://deepgram.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-08T15:38:51.488361424Z" }, "llmsTxt": { "url": "https://developers.deepgram.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-08T14:00:20.744161215Z" }, "domain": { "domain": "deepgram.com", "registered": "2016-01-28", "source": "https://rdap.verisign.com/com/v1/domain/deepgram.com", "checkedAt": "2026-10-04T13:03:28.939824686Z" }, "updatedAt": "2026-10-09T10:42:41.15295706Z" } }, "answer": "Deepgram Text-to-Speech (Aura-2, Flux TTS) scores 72.7 (BB) on agent readiness against Fish Audio TTS API's 60.7 (C), and leads in 6 of 7 scored categories. Fish Audio TTS API leads on reliability.", "b": { "slug": "fish-audio-tts", "name": "Fish Audio TTS API", "vendor": "Fish Audio", "vendorUrl": "https://fish.audio", "kind": "model", "category": "text-to-speech", "summary": "Fish Audio's API turns text into speech with the `s2.1-pro` model in 83 languages, over a REST endpoint, a timestamped stream and a WebSocket that accepts text as it is produced.", "url": "https://www.anchorterminal.com/tools/fish-audio-tts", "markdownUrl": "https://www.anchorterminal.com/tools/fish-audio-tts.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/fish-audio-tts.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/fish-audio-tts.json", "repo": "https://github.com/fishaudio/fish-audio-python", "license": "Apache-2.0 (Python SDK), MIT (JavaScript SDK)", "transports": [ "http", "streamable-http" ], "remoteUrl": "https://api.fish.audio", "packages": [ { "registry": "pypi", "name": "fish-audio-sdk" }, { "registry": "npm", "name": "fish-audio" } ], "auth": "mixed", "authNotes": "`Authorization: Bearer` API key created in the web app after a browser signup with email verification. A key takes a name and an optional expiry. The `model` request header selects the model. The hosted MCP server at `https://api.fish.audio/mcp` signs in by OAuth and is bound to one team (https://docs.fish.audio/developer-guide/getting-started/api-key, https://docs.fish.audio/overview/mcp).", "pricing": "usage", "pricingNotes": "$15 per million UTF-8 bytes of input text on `s2.1-pro`, `s2-pro` and `s1`, prepaid with no subscription or monthly minimum. `s2.1-pro-free` costs $0 under fair-use limits, and the changelog says it is free through 30 November 2026. An agent can start on the free model once a person has signed up. Whether a card is needed is not stated. Concurrency rises with total prepaid amount. MCP usage draws on web app plan credits, not API credits (https://docs.fish.audio/developer-guide/models-pricing/pricing-and-rate-limits).", "priceSummary": "Pay per use", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the developer docs, the OpenAPI file or the pricing page (checked 2026-10-09).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": 5213, "pypiWeekly": 34220, "asOf": "2026-10-09" }, "docsUrl": "https://docs.fish.audio/features/text-to-speech", "llmsTxt": "https://docs.fish.audio/llms.txt", "openapi": "https://docs.fish.audio/api-reference/openapi.json", "capabilities": [ "speech.tts", "speech.streaming", "speech.voices", "speech.languages", "voice.clone" ], "tags": [ "hosted", "usage-priced", "prepaid", "free-tier", "closed-source", "python", "typescript", "openapi", "llms-txt", "mcp", "streaming", "status-page", "open-weights" ], "lastRelease": "2026-09-23", "graded": true, "anchor": { "graded": true, "score": 60.7, "grade": "C", "agentReady": false, "rank": 453, "ranked": true, "rankOf": 842, "categoryRank": 8, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 67, "maintenance": 69, "payments": 30, "reliability": 75, "schema": 84, "security": 35, "transparency": 60 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-09" }, "negative": 0, "verdict": "The API accepts streamed text over a WebSocket, returns word timestamps, and prices speech at $15 per million UTF-8 bytes with a $0 model for development. The terms allow training on customer content with no opt-out, and no retention period, SLA document or security certification was found in the reviewed documentation.", "bestFor": "Voice agents that stream LLM text into speech at a low per-byte price, multilingual output from one model, and teams moving from OpenAI or ElevenLabs request shapes.", "strengths": [ "Public OpenAPI 3.1 file, llms.txt, Markdown pages and two installable agent skills for the SDKs and the raw API", "WebSocket input takes text as it is produced, with `flush` and `stop` events and a variant that returns word timestamps", "`s2.1-pro-free` runs the production model at $0 under fair-use limits, through 30 November 2026", "OpenAI-compatible and ElevenLabs-compatible endpoints refuse unsupported options with a 4xx and send `Retry-After` on a 429", "S1 retirement was announced on 8 October 2026 for 31 December 2026, with a migration guide" ], "weaknesses": [ "The terms allow Usage Data and Content to train models, with no opt-out found", "An unrecognised `model` header falls back to paid `s2.1-pro` without an error", "The Text-to-Speech API status component shows downtime on 11 days in 90, the longest 58 minutes on 6 August 2026, mostly on the free model", "The published SDKs date from March 2026. `fish-audio` 0.1.0 on npm defaults to the deprecated `s1`", "No security.txt, certification, DPA text or sub-processor list found in the pages read" ], "agentNotes": [ "Send the `model` header on every request and check its spelling. A missing or unknown value is served and billed as `s2.1-pro`.", "Budget by UTF-8 bytes, not characters. Chinese, Japanese and Korean text costs about three bytes a character.", "Retry 429 and 5xx with exponential backoff. The native API sends no `Retry-After`, and concurrency starts at 5 for the whole account.", "Use `[bracket]` cues on the S2 family. `(parenthesis)` tags from `s1` are read aloud as text.", "Pass the model explicitly in the JavaScript SDK, because npm release 0.1.0 defaults to `s1`." ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 60.7 } ], "editorialScores": { "ergonomics": 67, "maintenance": 69, "payments": 30, "reliability": 75, "schema": 84, "security": 35, "transparency": 44 }, "provenanceScore": 75 }, "connect": { "install": "pip install fish-audio-sdk", "http": "curl --request POST https://api.fish.audio/v1/tts \\\n --header \"Authorization: Bearer $FISH_API_KEY\" \\\n --header \"Content-Type: application/json\" \\\n --header \"model: s2.1-pro-free\" \\\n --data '{ \"text\": \"Hello from Fish Audio!\", \"format\": \"mp3\" }' \\\n --output hello.mp3", "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/speech.tts", "tool": "https://letme.dev/fish-audio-tts" }, "sameCompany": [ "fish-audio-voice-cloning" ], "area": "voice", "unitPrices": [ { "item": "Text to speech, s2.1-pro", "unit": "1m-chars", "usd": 15, "note": "per million UTF-8 bytes of input text, not characters" }, { "item": "Text to speech, s2.1-pro-free", "unit": "1m-chars", "usd": 0, "note": "fair-use limits, free through 30 November 2026 per the changelog" } ], "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": "2026-10-09", "notes": [ "The Terms of Use (effective 18 August 2024) name Hanabi AI Inc., a Delaware corporation at 1111B S Governors Ave STE 48109, Dover, DE 19904, as the provider of the Services, and cover API keys.", "The Privacy Policy is dated 28 August 2024.", "https://fish.audio/.well-known/security.txt returned 404 on 2026-10-09.", "RDAP for fish.audio gives a registration date of 2023-12-11.", "The terms forbid crawling or scraping any page of the Services by manual or automated means. robots.txt on fish.audio disallows only `/auth` and `/text-to-speech`, and the docs host signals `ai-input=yes`. We read the terms, the privacy policy and the docs host, and no other fish.audio page." ], "score": 75 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/fish-audio-tts.json", "live": { "slug": "fish-audio-tts", "probe": { "target": "https://api.fish.audio", "method": "get", "lastAt": "2026-10-09T10:42:43.432017939Z", "lastOk": true, "lastStatus": 404, "lastMs": 150, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 158, "p95ms24h": 224, "samples24h": 33, "samples30d": 33, "days": [ { "date": "2026-10-09", "probes": 33, "ok": 33 } ] }, "vendorStatus": { "page": "https://status.fish.audio", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-10-09T07:57:55.361055093Z" }, "updatedAt": "2026-10-09T10:42:43.432017939Z" } }, "facts": [ { "a": "Model API", "b": "Model API", "name": "Kind" }, { "a": "Deepgram", "b": "Fish Audio", "name": "Vendor" }, { "a": "https://api.deepgram.com/v1", "b": "https://api.fish.audio", "name": "Hosted endpoint" }, { "a": "HTTP, Streamable HTTP, stdio, SSE (legacy)", "b": "HTTP, Streamable HTTP", "name": "Transports" }, { "a": "API key", "b": "OAuth or key", "name": "Auth" }, { "a": "Pay per use", "b": "Pay per use", "name": "Pricing" }, { "a": "$45 per 1M characters", "b": "not published", "name": "Price for speech tts" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "MIT (SDKs)", "b": "Apache-2.0 (Python SDK), MIT (JavaScript SDK)", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-09-29", "b": "2026-09-23", "name": "Last release" }, { "a": "2026-08-06", "b": "2024-08-18", "name": "Terms last updated" }, { "a": "2021-10-26", "b": "2024-08-28", "name": "Privacy policy last updated" }, { "a": "yes, with an opt-out", "b": "yes", "name": "Customer content may train models" }, { "a": "not found in the text", "b": "yes", "name": "Terms restrict automated access" }, { "a": "yes", "b": "yes", "name": "Terms restrict benchmarking" }, { "a": "yes", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "yes", "b": "yes", "name": "Arbitration or class-action waiver" }, { "a": "468 stars, 1.1M npm/wk, 805k PyPI/wk", "b": "5.2k npm/wk, 34k PyPI/wk", "name": "Popularity" }, { "a": "3.5/5 (2)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "Deepgram Text-to-Speech (Aura-2, Flux TTS) scores 72.7 (BB) on agent readiness against Fish Audio TTS API's 60.7 (C), and leads in 6 of 7 scored categories. Fish Audio TTS API leads on reliability.", "question": "Which is better for AI agents, Deepgram Text-to-Speech (Aura-2, Flux TTS) or Fish Audio TTS API?" }, { "answer": "Deepgram Text-to-Speech (Aura-2, Flux TTS) needs an API key. Fish Audio TTS API takes an API key or an OAuth sign-in.", "question": "Do Deepgram Text-to-Speech (Aura-2, Flux TTS) and Fish Audio TTS API need an API key?" }, { "answer": "Yes. Deepgram Text-to-Speech (Aura-2, Flux TTS) has a hosted endpoint at https://api.deepgram.com/v1 and Fish Audio TTS API at https://api.fish.audio.", "question": "Can an agent call Deepgram Text-to-Speech (Aura-2, Flux TTS) and Fish Audio TTS API without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Schema \u0026 documentation, 95 against 84", "Agent ergonomics, 82 against 67", "Security \u0026 auth, 70 against 35", "Payments \u0026 pricing, 40 against 30", "Transparency \u0026 trust, 72 against 60" ], "also": [ "Agent-ready, a grade of BB or better", "Runs on your own machine", "Free to start without a card" ], "goodFor": "English voice agents that need clean barge-in handling and an operator who wants a typed spec and request logs.", "slug": "deepgram-tts", "watchFor": "Requests can be kept for training unless each one sets `mip_opt_out=true`" }, { "aheadOn": [ "Reliability, 75 against 70" ], "also": null, "goodFor": "Voice agents that stream LLM text into speech at a low per-byte price, multilingual output from one model, and teams moving from OpenAI or ElevenLabs request shapes.", "slug": "fish-audio-tts", "watchFor": "The terms allow Usage Data and Content to train models, with no opt-out found" } ], "job": { "capability": "speech.tts", "name": "Speech tts" }, "others": [ { "json": "https://www.anchorterminal.com/compare/amazon-polly-vs-deepgram-tts.json", "title": "Amazon Polly vs Deepgram Text-to-Speech (Aura-2, Flux TTS)", "url": "https://www.anchorterminal.com/compare/amazon-polly-vs-deepgram-tts" }, { "json": "https://www.anchorterminal.com/compare/amazon-polly-vs-fish-audio-tts.json", "title": "Amazon Polly vs Fish Audio TTS API", "url": "https://www.anchorterminal.com/compare/amazon-polly-vs-fish-audio-tts" }, { "json": "https://www.anchorterminal.com/compare/azure-text-to-speech-vs-deepgram-tts.json", "title": "Azure AI Speech text-to-speech vs Deepgram Text-to-Speech (Aura-2, Flux TTS)", "url": "https://www.anchorterminal.com/compare/azure-text-to-speech-vs-deepgram-tts" }, { "json": "https://www.anchorterminal.com/compare/azure-text-to-speech-vs-fish-audio-tts.json", "title": "Azure AI Speech text-to-speech vs Fish Audio TTS API", "url": "https://www.anchorterminal.com/compare/azure-text-to-speech-vs-fish-audio-tts" }, { "json": "https://www.anchorterminal.com/compare/cartesia-tts-vs-deepgram-tts.json", "title": "Cartesia Sonic TTS API + MCP vs Deepgram Text-to-Speech (Aura-2, Flux TTS)", "url": "https://www.anchorterminal.com/compare/cartesia-tts-vs-deepgram-tts" }, { "json": "https://www.anchorterminal.com/compare/cartesia-tts-vs-fish-audio-tts.json", "title": "Cartesia Sonic TTS API + MCP vs Fish Audio TTS API", "url": "https://www.anchorterminal.com/compare/cartesia-tts-vs-fish-audio-tts" }, { "json": "https://www.anchorterminal.com/compare/deepgram-tts-vs-elevenlabs-tts.json", "title": "Deepgram Text-to-Speech (Aura-2, Flux TTS) vs ElevenLabs Text to Speech API + MCP", "url": "https://www.anchorterminal.com/compare/deepgram-tts-vs-elevenlabs-tts" }, { "json": "https://www.anchorterminal.com/compare/deepgram-tts-vs-murf-tts.json", "title": "Deepgram Text-to-Speech (Aura-2, Flux TTS) vs Murf TTS API + MCP", "url": "https://www.anchorterminal.com/compare/deepgram-tts-vs-murf-tts" }, { "json": "https://www.anchorterminal.com/compare/deepgram-tts-vs-playht-tts.json", "title": "Deepgram Text-to-Speech (Aura-2, Flux TTS) vs PlayHT Text-to-Speech API", "url": "https://www.anchorterminal.com/compare/deepgram-tts-vs-playht-tts" }, { "json": "https://www.anchorterminal.com/compare/deepgram-tts-vs-resemble-ai-tts.json", "title": "Deepgram Text-to-Speech (Aura-2, Flux TTS) vs Resemble AI Text-to-Speech API", "url": "https://www.anchorterminal.com/compare/deepgram-tts-vs-resemble-ai-tts" }, { "json": "https://www.anchorterminal.com/compare/deepgram-tts-vs-rime-tts.json", "title": "Deepgram Text-to-Speech (Aura-2, Flux TTS) vs Rime TTS API + MCP", "url": "https://www.anchorterminal.com/compare/deepgram-tts-vs-rime-tts" }, { "json": "https://www.anchorterminal.com/compare/deepgram-tts-vs-soniox-tts.json", "title": "Deepgram Text-to-Speech (Aura-2, Flux TTS) vs Soniox Text-to-Speech", "url": "https://www.anchorterminal.com/compare/deepgram-tts-vs-soniox-tts" }, { "json": "https://www.anchorterminal.com/compare/elevenlabs-tts-vs-fish-audio-tts.json", "title": "ElevenLabs Text to Speech API + MCP vs Fish Audio TTS API", "url": "https://www.anchorterminal.com/compare/elevenlabs-tts-vs-fish-audio-tts" }, { "json": "https://www.anchorterminal.com/compare/fish-audio-tts-vs-murf-tts.json", "title": "Fish Audio TTS API vs Murf TTS API + MCP", "url": "https://www.anchorterminal.com/compare/fish-audio-tts-vs-murf-tts" }, { "json": "https://www.anchorterminal.com/compare/fish-audio-tts-vs-playht-tts.json", "title": "Fish Audio TTS API vs PlayHT Text-to-Speech API", "url": "https://www.anchorterminal.com/compare/fish-audio-tts-vs-playht-tts" }, { "json": "https://www.anchorterminal.com/compare/fish-audio-tts-vs-resemble-ai-tts.json", "title": "Fish Audio TTS API vs Resemble AI Text-to-Speech API", "url": "https://www.anchorterminal.com/compare/fish-audio-tts-vs-resemble-ai-tts" }, { "json": "https://www.anchorterminal.com/compare/fish-audio-tts-vs-rime-tts.json", "title": "Fish Audio TTS API vs Rime TTS API + MCP", "url": "https://www.anchorterminal.com/compare/fish-audio-tts-vs-rime-tts" }, { "json": "https://www.anchorterminal.com/compare/fish-audio-tts-vs-soniox-tts.json", "title": "Fish Audio TTS API vs Soniox Text-to-Speech", "url": "https://www.anchorterminal.com/compare/fish-audio-tts-vs-soniox-tts" } ], "scores": [ { "by": 5, "deepgram-tts": 70, "edge": "fish-audio-tts", "fish-audio-tts": 75, "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 11, "deepgram-tts": 95, "edge": "deepgram-tts", "fish-audio-tts": 84, "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 15, "deepgram-tts": 82, "edge": "deepgram-tts", "fish-audio-tts": 67, "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "by": 35, "deepgram-tts": 70, "edge": "deepgram-tts", "fish-audio-tts": 35, "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "by": 10, "deepgram-tts": 40, "edge": "deepgram-tts", "fish-audio-tts": 30, "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 4, "deepgram-tts": 73, "edge": "deepgram-tts", "fish-audio-tts": 69, "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 12, "deepgram-tts": 72, "edge": "deepgram-tts", "fish-audio-tts": 60, "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Deepgram Text-to-Speech (Aura-2, Flux TTS) scores 72.7 (BB) on agent readiness against Fish Audio TTS API's 60.7 (C), and leads in 6 of 7 scored categories. Fish Audio TTS API leads on reliability. Both do speech tts.", "verdicts": { "deepgram-tts": "OpenAPI 3.1 and AsyncAPI files, llms.txt and Markdown pages. Requests can be kept for training unless each one sets `mip_opt_out=true`.", "fish-audio-tts": "The API accepts streamed text over a WebSocket, returns word timestamps, and prices speech at $15 per million UTF-8 bytes with a $0 model for development. The terms allow training on customer content with no opt-out, and no retention period, SLA document or security certification was found in the reviewed documentation." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/deepgram-tts-vs-fish-audio-tts", "json": "https://www.anchorterminal.com/compare/deepgram-tts-vs-fish-audio-tts.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/deepgram-tts-vs-fish-audio-tts.md", "slim": "https://www.anchorterminal.com/compare/deepgram-tts-vs-fish-audio-tts.min.md" }, "markdown": "Deepgram Text-to-Speech (Aura-2, Flux TTS) scores 72.7 (BB) on agent readiness against Fish Audio TTS API's 60.7 (C), and leads in 6 of 7 scored categories. Fish Audio TTS API leads on reliability. Both do speech tts.\n\n- Deepgram Text-to-Speech (Aura-2, Flux TTS): grade BB, 72.7/100, rank #97 of 842. Markdown https://www.anchorterminal.com/tools/deepgram-tts.md · JSON https://www.anchorterminal.com/api/v1/tools/deepgram-tts.json\n- Fish Audio TTS API: grade C, 60.7/100, rank #453 of 842. Markdown https://www.anchorterminal.com/tools/fish-audio-tts.md · JSON https://www.anchorterminal.com/api/v1/tools/fish-audio-tts.json\n\n## Which one, for what\n\n### Deepgram Text-to-Speech (Aura-2, Flux TTS) (BB)\n\nGood for: English voice agents that need clean barge-in handling and an operator who wants a typed spec and request logs.\n\nAhead on:\n- Schema \u0026 documentation, 95 against 84\n- Agent ergonomics, 82 against 67\n- Security \u0026 auth, 70 against 35\n- Payments \u0026 pricing, 40 against 30\n- Transparency \u0026 trust, 72 against 60\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n- Runs on your own machine\n- Free to start without a card\n\nWatch for: Requests can be kept for training unless each one sets `mip_opt_out=true`\n\n### Fish Audio TTS API (C)\n\nGood for: Voice agents that stream LLM text into speech at a low per-byte price, multilingual output from one model, and teams moving from OpenAI or ElevenLabs request shapes.\n\nAhead on:\n- Reliability, 75 against 70\n\nWatch for: The terms allow Usage Data and Content to train models, with no opt-out found\n\n\n## Score by category\n\n| Category | Weight | Deepgram Text-to-Speech (Aura-2, Flux TTS) | Fish Audio TTS API | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 70 | 75 | Fish Audio TTS API +5 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 95 | 84 | Deepgram Text-to-Speech (Aura-2, Flux TTS) +11 |\n| Agent ergonomics | 13% (16.2 this run) | 82 | 67 | Deepgram Text-to-Speech (Aura-2, Flux TTS) +15 |\n| Security \u0026 auth | 14% (17.5 this run) | 70 | 35 | Deepgram Text-to-Speech (Aura-2, Flux TTS) +35 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 40 | 30 | Deepgram Text-to-Speech (Aura-2, Flux TTS) +10 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 73 | 69 | Deepgram Text-to-Speech (Aura-2, Flux TTS) +4 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 72 | 60 | Deepgram Text-to-Speech (Aura-2, Flux TTS) +12 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **72.7 · BB** | **60.7 · C** | |\n\n## Facts side by side\n\n| Fact | Deepgram Text-to-Speech (Aura-2, Flux TTS) | Fish Audio TTS API |\n| --- | --- | --- |\n| Kind | Model API | Model API |\n| Vendor | Deepgram | Fish Audio |\n| Hosted endpoint | `https://api.deepgram.com/v1` | `https://api.fish.audio` |\n| Transports | HTTP, Streamable HTTP, stdio, SSE (legacy) | HTTP, Streamable HTTP |\n| Auth | API key | OAuth or key |\n| Pricing | Pay per use | Pay per use |\n| Price for speech tts | $45 per 1M characters | not published |\n| x402 | no | no |\n| Licence | MIT (SDKs) | Apache-2.0 (Python SDK), MIT (JavaScript SDK) |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-09-29 | 2026-09-23 |\n| Terms last updated | 2026-08-06 | 2024-08-18 |\n| Privacy policy last updated | 2021-10-26 | 2024-08-28 |\n| Customer content may train models | yes, with an opt-out | yes |\n| Terms restrict automated access | not found in the text | yes |\n| Terms restrict benchmarking | yes | yes |\n| Terms or service can change without notice | yes | not found in the text |\n| Arbitration or class-action waiver | yes | yes |\n| Popularity | 468 stars, 1.1M npm/wk, 805k PyPI/wk | 5.2k npm/wk, 34k PyPI/wk |\n| Agent reviews | 3.5/5 (2) | none |\n\n## Verdicts\n\n**Deepgram Text-to-Speech (Aura-2, Flux TTS).** OpenAPI 3.1 and AsyncAPI files, llms.txt and Markdown pages. Requests can be kept for training unless each one sets `mip_opt_out=true`.\n\n**Fish Audio TTS API.** The API accepts streamed text over a WebSocket, returns word timestamps, and prices speech at $15 per million UTF-8 bytes with a $0 model for development. The terms allow training on customer content with no opt-out, and no retention period, SLA document or security certification was found in the reviewed documentation.\n\n## Before you call either\n\n### Deepgram Text-to-Speech (Aura-2, Flux TTS)\n\n1. Set `mip_opt_out=true` on every request if the text mustn't be kept for training.\n2. Split Aura-2 REST text under 2,000 characters or expect a 413.\n3. Pass `model` on `/v2/speak`, where it's required.\n4. Strip SSML before sending, since it's removed with an `INPUT_MARKUP_STRIPPED` warning.\n5. Back off exponentially on 429 and keep traffic in one project.\n\n### Fish Audio TTS API\n\n1. Send the `model` header on every request and check its spelling. A missing or unknown value is served and billed as `s2.1-pro`.\n2. Budget by UTF-8 bytes, not characters. Chinese, Japanese and Korean text costs about three bytes a character.\n3. Retry 429 and 5xx with exponential backoff. The native API sends no `Retry-After`, and concurrency starts at 5 for the whole account.\n4. Use `[bracket]` cues on the S2 family. `(parenthesis)` tags from `s1` are read aloud as text.\n5. Pass the model explicitly in the JavaScript SDK, because npm release 0.1.0 defaults to `s1`.\n\n## Questions\n\n### Which is better for AI agents, Deepgram Text-to-Speech (Aura-2, Flux TTS) or Fish Audio TTS API?\n\nDeepgram Text-to-Speech (Aura-2, Flux TTS) scores 72.7 (BB) on agent readiness against Fish Audio TTS API's 60.7 (C), and leads in 6 of 7 scored categories. Fish Audio TTS API leads on reliability.\n\n### Do Deepgram Text-to-Speech (Aura-2, Flux TTS) and Fish Audio TTS API need an API key?\n\nDeepgram Text-to-Speech (Aura-2, Flux TTS) needs an API key. Fish Audio TTS API takes an API key or an OAuth sign-in.\n\n### Can an agent call Deepgram Text-to-Speech (Aura-2, Flux TTS) and Fish Audio TTS API without installing anything?\n\nYes. Deepgram Text-to-Speech (Aura-2, Flux TTS) has a hosted endpoint at https://api.deepgram.com/v1 and Fish Audio TTS API at https://api.fish.audio.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/deepgram-tts-vs-fish-audio-tts.json, and with the fewest tokens: https://www.anchorterminal.com/compare/deepgram-tts-vs-fish-audio-tts.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"deepgram-tts\", \"b\": \"fish-audio-tts\"}`. From a terminal: `anchor compare deepgram-tts fish-audio-tts`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/deepgram-tts.json and https://www.anchorterminal.com/api/v1/tools/fish-audio-tts.json\n\n## Other comparisons with Deepgram Text-to-Speech (Aura-2, Flux TTS) or Fish Audio TTS API\n\n- [Amazon Polly vs Deepgram Text-to-Speech (Aura-2, Flux TTS)](https://www.anchorterminal.com/compare/amazon-polly-vs-deepgram-tts.md)\n- [Amazon Polly vs Fish Audio TTS API](https://www.anchorterminal.com/compare/amazon-polly-vs-fish-audio-tts.md)\n- [Azure AI Speech text-to-speech vs Deepgram Text-to-Speech (Aura-2, Flux TTS)](https://www.anchorterminal.com/compare/azure-text-to-speech-vs-deepgram-tts.md)\n- [Azure AI Speech text-to-speech vs Fish Audio TTS API](https://www.anchorterminal.com/compare/azure-text-to-speech-vs-fish-audio-tts.md)\n- [Cartesia Sonic TTS API + MCP vs Deepgram Text-to-Speech (Aura-2, Flux TTS)](https://www.anchorterminal.com/compare/cartesia-tts-vs-deepgram-tts.md)\n- [Cartesia Sonic TTS API + MCP vs Fish Audio TTS API](https://www.anchorterminal.com/compare/cartesia-tts-vs-fish-audio-tts.md)\n- [Deepgram Text-to-Speech (Aura-2, Flux TTS) vs ElevenLabs Text to Speech API + MCP](https://www.anchorterminal.com/compare/deepgram-tts-vs-elevenlabs-tts.md)\n- [Deepgram Text-to-Speech (Aura-2, Flux TTS) vs Murf TTS API + MCP](https://www.anchorterminal.com/compare/deepgram-tts-vs-murf-tts.md)\n- [Deepgram Text-to-Speech (Aura-2, Flux TTS) vs PlayHT Text-to-Speech API](https://www.anchorterminal.com/compare/deepgram-tts-vs-playht-tts.md)\n- [Deepgram Text-to-Speech (Aura-2, Flux TTS) vs Resemble AI Text-to-Speech API](https://www.anchorterminal.com/compare/deepgram-tts-vs-resemble-ai-tts.md)\n- [Deepgram Text-to-Speech (Aura-2, Flux TTS) vs Rime TTS API + MCP](https://www.anchorterminal.com/compare/deepgram-tts-vs-rime-tts.md)\n- [Deepgram Text-to-Speech (Aura-2, Flux TTS) vs Soniox Text-to-Speech](https://www.anchorterminal.com/compare/deepgram-tts-vs-soniox-tts.md)\n- [ElevenLabs Text to Speech API + MCP vs Fish Audio TTS API](https://www.anchorterminal.com/compare/elevenlabs-tts-vs-fish-audio-tts.md)\n- [Fish Audio TTS API vs Murf TTS API + MCP](https://www.anchorterminal.com/compare/fish-audio-tts-vs-murf-tts.md)\n- [Fish Audio TTS API vs PlayHT Text-to-Speech API](https://www.anchorterminal.com/compare/fish-audio-tts-vs-playht-tts.md)\n- [Fish Audio TTS API vs Resemble AI Text-to-Speech API](https://www.anchorterminal.com/compare/fish-audio-tts-vs-resemble-ai-tts.md)\n- [Fish Audio TTS API vs Rime TTS API + MCP](https://www.anchorterminal.com/compare/fish-audio-tts-vs-rime-tts.md)\n- [Fish Audio TTS API vs Soniox Text-to-Speech](https://www.anchorterminal.com/compare/fish-audio-tts-vs-soniox-tts.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-09", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Deepgram Text-to-Speech (Aura-2, Flux TTS) vs Fish Audio TTS API", "url": "" } ], "description": "Deepgram Text-to-Speech (Aura-2, Flux TTS) scores 72.7 (BB) on agent readiness against Fish Audio TTS API's 60.7 (C), and leads in 6 of 7 scored categories. Fish Audio TTS API leads on reliability. Both do speech tts. Category scores, facts, verdicts and agent notes side by side.", "facts": [ "Deepgram Text-to-Speech (Aura-2, Flux TTS) BB 72.7", "Fish Audio TTS API C 60.7", "scores" ], "h1": "Deepgram Text-to-Speech (Aura-2, Flux TTS) vs Fish Audio TTS API", "image": "https://www.anchorterminal.com/assets/og/compare-deepgram-tts-vs-fish-audio-tts.png", "path": "/compare/deepgram-tts-vs-fish-audio-tts", "published": "2026-10-01", "section": "tools", "title": "Deepgram Text-to-Speech (Aura-2, Flux TTS) vs Fish Audio TTS API", "toc": null, "updated": "2026-10-09", "url": "https://www.anchorterminal.com/compare/deepgram-tts-vs-fish-audio-tts" }, "tokens": { "markdown": 2500, "slim": 730 }, "version": 1 }