{ "data": { "a": { "slug": "cartesia-tts", "name": "Cartesia Sonic TTS API + MCP", "vendor": "Cartesia", "vendorUrl": "https://cartesia.ai", "kind": "model", "category": "text-to-speech", "summary": "Sonic text-to-speech, currently `sonic-3.6` in 44 languages, over `/tts/bytes`, `/tts/sse` and a WebSocket that takes streamed LLM text with contexts and word timestamps.", "url": "https://www.anchorterminal.com/tools/cartesia-tts", "markdownUrl": "https://www.anchorterminal.com/tools/cartesia-tts.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/cartesia-tts.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/cartesia-tts.json", "repo": "https://github.com/cartesia-ai/cartesia-python", "license": "Apache-2.0 (SDKs)", "transports": [ "http", "streamable-http", "stdio" ], "remoteUrl": "https://api.cartesia.ai", "packages": [ { "registry": "npm", "name": "@cartesia/cartesia-js" }, { "registry": "pypi", "name": "cartesia" }, { "registry": "pypi", "name": "cartesia-mcp" } ], "auth": "mixed", "authNotes": "`Authorization: Bearer` API key plus a required `Cartesia-Version` date header (currently `2026-08-14`). Browsers should use short-lived access tokens minted server-side. The hosted MCP at `https://mcp.cartesia.ai/mcp` signs in through the Playground and creates an MCP key. The local `cartesia-mcp` reads `CARTESIA_API_KEY`.", "pricing": "freemium", "pricingNotes": "TTS costs about 1 credit a character, charged only on successful requests. Free has 20,000 credits a month (about 27 minutes of Sonic 3.6), Pro $5 100,000, Startup $49 1.25M and Scale $299 8M. Overages, if enabled, cost $65 per 1M credits on Pro, $45 on Startup and $38 on Scale. Commercial use starts at Pro. Unused credits roll over up to 2 times the monthly amount (https://cartesia.ai/pricing).", "priceSummary": "$5 / mo", "where": "both", "x402": { "level": "no", "evidence": "No x402 or machine payment in the docs or pricing (checked 2026-09-30).", "endpoints": [] }, "toolCount": 15, "popularity": { "githubStars": 133, "npmWeekly": 166023, "pypiWeekly": 176771, "asOf": "2026-09-30" }, "docsUrl": "https://docs.cartesia.ai/build-with-cartesia/tts-models/latest", "llmsTxt": "https://docs.cartesia.ai/llms.txt", "capabilities": [ "speech.tts", "speech.streaming", "speech.voices", "speech.ssml", "speech.languages" ], "tags": [ "hosted", "freemium", "free-tier", "closed-source", "python", "typescript", "llms-txt", "mcp", "streaming", "enterprise" ], "lastRelease": "2026-09-30", "graded": true, "anchor": { "graded": true, "score": 63.8, "grade": "B", "agentReady": false, "rank": 375, "ranked": true, "rankOf": 961, "categoryRank": 7, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 65, "maintenance": 79, "payments": 30, "reliability": 63, "schema": 86, "security": 58, "transparency": 67 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": 0, "verdict": "WebSocket input accepts streamed LLM text with contexts, flushing and word timestamps. Five TTS incidents on the status page between 29 July and 21 August 2026.", "bestFor": "Real-time voice agents that stream LLM output straight into speech and need stable, pinnable models.", "strengths": [ "WebSocket input accepts streamed LLM text with contexts, flushing and word timestamps", "Dated model snapshots such as `sonic-3.6-2026-08-27` never change, and `Cartesia-Version` pins the API shape", "OpenAPI and AsyncAPI files per API version listed in llms.txt", "Short-lived access tokens with TTS, STT and agent grants for browser clients", "Deprecations dated in the changelog, Sonic-2 and Sonic Turbo sunset after 2026-10-20" ], "weaknesses": [ "Five TTS incidents on the status page between 29 July and 21 August 2026", "TTS concurrency is 2 on Free, 3 on Pro, 5 on Startup and 15 on Scale", "The Terms allow training on inputs and outputs unless you opt out by form", "Zero data retention is Enterprise only", "No SLA, and no error responses documented for the TTS endpoints" ], "agentNotes": [ "Send the `Cartesia-Version` header on every request.", "Pin a dated snapshot such as `sonic-3.6-2026-08-27` if output must not change.", "Move off `sonic-2`, `sonic-turbo` and `sonic-3-2025-10-27` before 2026-10-20.", "Expect a 429 at the plan's concurrency limit and queue requests yourself.", "Mint a short-lived access token for browser clients instead of shipping the API key." ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 63.8 } ], "editorialScores": { "ergonomics": 65, "maintenance": 79, "payments": 30, "reliability": 63, "schema": 86, "security": 58, "transparency": 60 }, "provenanceScore": 74 }, "connect": { "http": "curl -X POST https://api.cartesia.ai/tts/bytes -H \"Authorization: Bearer $CARTESIA_API_KEY\" \\\n -H \"Cartesia-Version: 2026-08-14\" -H \"content-type: application/json\" -o speech.wav \\\n -d '{\"model_id\":\"sonic-3.6\",\"transcript\":\"Your table is booked for seven.\",\"voice\":{\"id\":\"47c38ca4-5f35-497b-b1a3-415245fb35e1\"},\"output_format\":{\"container\":\"wav\",\"encoding\":\"pcm_s16le\",\"sample_rate\":44100}}'", "claudeCode": "claude mcp add --transport http --scope user cartesia https://mcp.cartesia.ai/mcp", "config": { "mcpServers": { "cartesia": { "args": [ "cartesia-mcp" ], "command": "uvx", "env": { "CARTESIA_API_KEY": "${CARTESIA_API_KEY}" } } } } }, "letme": { "capability": "https://letme.dev/speech.tts", "tool": "https://letme.dev/cartesia-tts" }, "sameCompany": [ "cartesia-ink-stt", "cartesia-voice-cloning" ], "area": "voice", "unitPrices": [ { "item": "Sonic TTS overage on Pro", "unit": "1m-chars", "usd": 65, "note": "about 1 credit a character, $65 per 1M credits" }, { "item": "Sonic TTS overage on Startup", "unit": "1m-chars", "usd": 45 }, { "item": "Sonic TTS overage on Scale", "unit": "1m-chars", "usd": 38 }, { "item": "Pro plan", "unit": "month", "usd": 5, "note": "100,000 credits" }, { "item": "Startup plan", "unit": "month", "usd": 49, "note": "1.25M credits" }, { "item": "Scale plan", "unit": "month", "usd": 299, "note": "8M credits" } ], "provenance": { "legalEntity": "Cartesia AI, Inc.", "domain": "cartesia.ai", "domainRegistered": "2023-05-10", "endpointOnVendorDomain": true, "terms": "https://www.cartesia.ai/legal/terms", "privacy": "https://www.cartesia.ai/legal/privacy", "statusPage": "https://status.cartesia.ai", "changelog": "https://docs.cartesia.ai/changelog/2026", "securityTxt": "none", "checked": "2026-09-30", "score": 74 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/cartesia-tts.json", "live": { "slug": "cartesia-tts", "probe": { "target": "https://api.cartesia.ai", "method": "get", "lastAt": "2026-10-11T02:46:20.900732344Z", "lastOk": true, "lastStatus": 200, "lastMs": 43, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 54, "p95ms24h": 121, "samples24h": 248, "samples30d": 2712, "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": 250, "ok": 250 }, { "date": "2026-10-10", "probes": 247, "ok": 247 }, { "date": "2026-10-11", "probes": 29, "ok": 29 } ] }, "vendorStatus": { "page": "https://status.cartesia.ai", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-10-11T02:40:35.909927804Z" }, "versions": [ { "registry": "github", "name": "cartesia-ai/cartesia-python", "version": "v4.2.0", "released": "2026-09-02", "seenAt": "2026-10-10T17:38:27.469179381Z" }, { "registry": "npm", "name": "@cartesia/cartesia-js", "version": "4.2.0", "seenAt": "2026-10-10T17:38:25.209636835Z" }, { "registry": "pypi", "name": "cartesia", "version": "4.2.0", "released": "2026-09-02", "seenAt": "2026-10-10T17:38:25.461635312Z" }, { "registry": "pypi", "name": "cartesia-mcp", "version": "0.26.1", "released": "2026-10-08", "seenAt": "2026-10-10T17:38:25.574205075Z" } ], "githubStars": 134, "npmWeekly": 83895, "pypiWeekly": 212834, "securityTxt": { "url": "https://cartesia.ai/.well-known/security.txt", "state": "valid", "expires": "2027-10-03T00:00:00.000Z", "checkedAt": "2026-10-10T15:41:16.780057635Z" }, "llmsTxt": { "url": "https://docs.cartesia.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-10T14:03:46.352974217Z" }, "domain": { "domain": "cartesia.ai", "registered": "2023-05-10", "source": "https://rdap.identitydigital.services/rdap/domain/cartesia.ai", "checkedAt": "2026-10-04T13:04:05.26596839Z" }, "pages": [ { "url": "https://docs.cartesia.ai/changelog/2026", "kind": "changelog", "status": 200, "checkedAt": "2026-10-08T18:18:24.003636335Z", "changedAt": "2026-10-07T18:04:49.25388057Z", "fingerprint": "405fadad924b" }, { "url": "https://cartesia.ai/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-10-10T18:58:05.914001972Z", "changedAt": "2026-10-09T18:33:36.400141534Z", "fingerprint": "12bd9269bdef" }, { "url": "https://www.cartesia.ai/legal/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-08T18:26:54.204830291Z", "changedAt": "2026-10-08T18:26:54.204830291Z", "fingerprint": "2750d7de8d7c" }, { "url": "https://www.cartesia.ai/legal/terms", "kind": "terms", "status": 200, "checkedAt": "2026-10-08T18:26:56.591248396Z", "changedAt": "2026-10-08T18:26:56.591248396Z", "fingerprint": "a146b5cf872a" } ], "updatedAt": "2026-10-11T02:46:20.900732344Z" } }, "answer": "HeyGen Voice scores 71.3 (BB) on agent readiness against Cartesia Sonic TTS API + MCP's 63.8 (B), and leads in 5 of 7 scored categories. Cartesia Sonic TTS API + MCP leads on maintenance \u0026 community.", "b": { "slug": "heygen-voice", "name": "HeyGen Voice", "vendor": "HeyGen", "vendorUrl": "https://www.heygen.com", "kind": "model", "category": "text-to-speech", "summary": "HeyGen Voice is HeyGen's in-house text-to-speech model, `heygen-voice-1`, which speaks text in a voice cloned from one recording (instant) or from 20 minutes or more (professional), through HeyGen's v3 API.", "url": "https://www.anchorterminal.com/tools/heygen-voice", "markdownUrl": "https://www.anchorterminal.com/tools/heygen-voice.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/heygen-voice.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/heygen-voice.json", "license": "Closed service under HeyGen's Terms of Service (HeyGen Technology, Inc., last updated 23 July 2026).", "transports": [ "http" ], "remoteUrl": "https://api.heygen.com", "packages": [], "auth": "api-key", "authNotes": "An API key from the HeyGen API dashboard, sent in the X-Api-Key header. Keys can be restricted to read and write scopes, and the speech and voice endpoints need voices:write. The OpenAPI file also accepts an OAuth bearer token, which bills subscription credits. Stripe Projects can provision a key through the operator's Stripe account.", "pricing": "usage", "pricingNotes": "Instant-voice speech is $15 per million submitted characters, charged only on successful requests (OpenAPI description, checked 10 October 2026). Professional speech is 0.6 API credits per generated minute, and each professional voice needs a purchased slot. Instant voices are free to create during the preview. No free API allowance was found.", "priceSummary": "Pay per use", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the developer llms.txt, the OpenAPI file or the HeyGen Voice pages, checked 10 October 2026. Keys are funded by API credit or through Stripe Projects.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-10" }, "docsUrl": "https://developers.heygen.com/docs/models/heygen-voice", "llmsTxt": "https://developers.heygen.com/llms.txt", "openapi": "https://developers.heygen.com/openapi/external-api.json", "capabilities": [ "speech.tts", "speech.streaming", "speech.languages", "voice.clone" ], "tags": [ "hosted", "official", "usage-priced", "closed-source", "openapi", "llms-txt", "streaming", "status-page", "soc2", "security-txt", "cli", "agent-skills" ], "graded": true, "anchor": { "graded": true, "score": 71.3, "grade": "BB", "agentReady": true, "rank": 131, "ranked": true, "rankOf": 961, "categoryRank": 5, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 83, "maintenance": 65, "payments": 30, "reliability": 75, "schema": 94, "security": 69, "transparency": 69 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-10" }, "negative": 0, "verdict": "HeyGen Voice has a typed OpenAPI contract, streaming with character timestamps, and a published price of $15 per million characters for instant voices, with failed requests not charged. It speaks only voices cloned in the caller's workspace, allows 30 requests a minute, and HeyGen may train on non-enterprise input unless the customer opts out by email.", "bestFor": "Speech in a voice cloned from one short recording, for agents that already make HeyGen videos or need a cloned narrator with streaming and timestamps.", "strengths": [ "OpenAPI 3.1 file with enums, ranges, `additionalProperties: false` and per-code errors for every speech and voice endpoint", "Streaming over Server-Sent Events, with optional character-level timestamps", "Instant-voice speech priced at $15 per million characters without a login, and failed or disconnected requests are not charged", "API keys can be restricted to read and write scopes, and the speech endpoints need voices:write", "Instant voices are created from one recording, usually ready within seconds, in 39 base languages" ], "weaknesses": [ "Speaks only voices cloned in the caller's workspace. Stock and designed voices go through a separate endpoint and engines", "30 requests a minute per workspace member on the speech endpoints, on every plan", "Output is a 44.1 kHz mono WAV only, and text is capped at 5,000 characters a request", "HeyGen's privacy policy allows training on user input, with an opt-out by email. Enterprise data is excluded by default", "No official SDK, no free API allowance and no SLA in the terms" ], "agentNotes": [ "Create a voice first with POST /v3/models/audio/voices and `mode`, then poll GET /v3/models/audio/voices/{voice_id} until `status` is ACTIVE before calling speech", "Send `expressiveness_boost` only for instant voices and `seed`, `speed`, `pitch_shift`, `pitch_variance` or `\u003cbreak\u003e` tags only for professional voices. Mixing them returns 400 invalid_parameter", "On the stream, decode and play each base64 WAV part in `part_index` order. Do not concatenate the bytes", "Send an Idempotency-Key when creating a voice, and retry 502, 503 and 504 on speech, which the OpenAPI file marks as safe", "Use POST /v3/voices/speech for stock or designed voices. It is a different engine and price" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "BB", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 71.3 } ], "editorialScores": { "ergonomics": 83, "maintenance": 65, "payments": 30, "reliability": 75, "schema": 94, "security": 69, "transparency": 52 }, "provenanceScore": 85 }, "connect": { "http": "curl -X POST \"https://api.heygen.com/v3/models/audio/tts\" \\\n -H \"X-Api-Key: $HEYGEN_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\"model\":\"heygen-voice-1\",\"voice_id\":\"\u003cVOICE_ID\u003e\",\"text\":\"Hello.\",\"language\":\"en\",\"expressiveness_boost\":0.8}'" }, "letme": { "capability": "https://letme.dev/speech.tts", "tool": "https://letme.dev/heygen-voice" }, "area": "voice", "unitPrices": [ { "item": "Instant-voice speech", "unit": "1m-chars", "usd": 15, "note": "Submitted Unicode characters, including spaces. Successful requests only." }, { "item": "Professional-voice speech", "unit": "audio-minute", "usd": 0.6, "note": "0.6 API credits per generated minute. The dollar figure assumes $1 a credit, from the OpenAPI example of 9/60 credit for $0.15." } ], "provenance": { "legalEntity": "HeyGen Technology, Inc.", "domain": "heygen.com", "domainRegistered": "", "endpointOnVendorDomain": true, "terms": "https://www.heygen.com/terms", "privacy": "https://www.heygen.com/privacy", "statusPage": "https://status.heygen.com", "changelog": "https://developers.heygen.com/changelog", "securityTxt": "valid", "checked": "2026-10-10", "notes": [ "security.txt at www.heygen.com/.well-known/security.txt names security@heygen.com and expires on 31 December 2026.", "The privacy policy names HeyGen Technology Inc. in section 1 and HeyGen, Inc. as processor in section 15.", "The status page has components per domain (www, app, api) and none for voice.", "Domain registration date was not checked." ], "score": 85 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/heygen-voice.json", "live": { "slug": "heygen-voice", "probe": { "target": "https://api.heygen.com", "method": "get", "lastAt": "2026-10-11T02:46:27.941825924Z", "lastOk": true, "lastStatus": 404, "lastMs": 308, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 301, "p95ms24h": 320, "samples24h": 30, "samples30d": 30, "days": [ { "date": "2026-10-10", "probes": 1, "ok": 1 }, { "date": "2026-10-11", "probes": 29, "ok": 29 } ] }, "vendorStatus": { "page": "https://status.heygen.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-10-11T02:40:57.349304573Z" }, "updatedAt": "2026-10-11T02:46:27.941825924Z" } }, "facts": [ { "a": "Model API", "b": "Model API", "name": "Kind" }, { "a": "Cartesia", "b": "HeyGen", "name": "Vendor" }, { "a": "https://api.cartesia.ai", "b": "https://api.heygen.com", "name": "Hosted endpoint" }, { "a": "HTTP, Streamable HTTP, stdio", "b": "HTTP", "name": "Transports" }, { "a": "OAuth or key", "b": "API key", "name": "Auth" }, { "a": "Freemium", "b": "Pay per use", "name": "Pricing" }, { "a": "$38 per 1M characters", "b": "not published", "name": "Price for text-to-speech" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache-2.0 (SDKs)", "b": "Closed service under HeyGen's Terms of Service (HeyGen Technology, Inc., last updated 23 July 2026).", "name": "Licence" }, { "a": "15", "b": "none", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-09-30", "b": "none", "name": "Last release" }, { "a": "2024-06-14", "b": "", "name": "Terms last updated" }, { "a": "2024-06-14", "b": "", "name": "Privacy policy last updated" }, { "a": "yes, with an opt-out", "b": "", "name": "Customer content may train models" }, { "a": "yes", "b": "", "name": "Terms restrict automated access" }, { "a": "yes", "b": "", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "", "name": "Terms or service can change without notice" }, { "a": "yes", "b": "", "name": "Arbitration or class-action waiver" }, { "a": "133 stars, 166k npm/wk, 177k PyPI/wk", "b": "none", "name": "Popularity" }, { "a": "3/5 (2)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "HeyGen Voice scores 71.3 (BB) on agent readiness against Cartesia Sonic TTS API + MCP's 63.8 (B), and leads in 5 of 7 scored categories. Cartesia Sonic TTS API + MCP leads on maintenance \u0026 community.", "question": "Which is better for AI agents, Cartesia Sonic TTS API + MCP or HeyGen Voice?" }, { "answer": "Cartesia Sonic TTS API + MCP takes an API key or an OAuth sign-in. HeyGen Voice needs an API key.", "question": "Do Cartesia Sonic TTS API + MCP and HeyGen Voice need an API key?" }, { "answer": "Yes. Cartesia Sonic TTS API + MCP has a hosted endpoint at https://api.cartesia.ai and HeyGen Voice at https://api.heygen.com.", "question": "Can an agent call Cartesia Sonic TTS API + MCP and HeyGen Voice without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Maintenance \u0026 community, 79 against 65" ], "also": [ "Runs on your own machine" ], "goodFor": "Real-time voice agents that stream LLM output straight into speech and need stable, pinnable models.", "slug": "cartesia-tts", "watchFor": "Five TTS incidents on the status page between 29 July and 21 August 2026" }, { "aheadOn": [ "Reliability, 75 against 63", "Schema \u0026 documentation, 94 against 86", "Agent ergonomics, 83 against 65", "Security \u0026 auth, 69 against 58" ], "also": [ "Agent-ready, a grade of BB or better" ], "goodFor": "Speech in a voice cloned from one short recording, for agents that already make HeyGen videos or need a cloned narrator with streaming and timestamps.", "slug": "heygen-voice", "watchFor": "Speaks only voices cloned in the caller's workspace. Stock and designed voices go through a separate endpoint and engines" } ], "job": { "capability": "speech.tts", "name": "Text-to-speech" }, "others": [ { "json": "https://www.anchorterminal.com/compare/amazon-polly-vs-cartesia-tts.json", "title": "Amazon Polly vs Cartesia Sonic TTS API + MCP", "url": "https://www.anchorterminal.com/compare/amazon-polly-vs-cartesia-tts" }, { "json": "https://www.anchorterminal.com/compare/amazon-polly-vs-heygen-voice.json", "title": "Amazon Polly vs HeyGen Voice", "url": "https://www.anchorterminal.com/compare/amazon-polly-vs-heygen-voice" }, { "json": "https://www.anchorterminal.com/compare/azure-text-to-speech-vs-cartesia-tts.json", "title": "Azure AI Speech text-to-speech vs Cartesia Sonic TTS API + MCP", "url": "https://www.anchorterminal.com/compare/azure-text-to-speech-vs-cartesia-tts" }, { "json": "https://www.anchorterminal.com/compare/azure-text-to-speech-vs-heygen-voice.json", "title": "Azure AI Speech text-to-speech vs HeyGen Voice", "url": "https://www.anchorterminal.com/compare/azure-text-to-speech-vs-heygen-voice" }, { "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-elevenlabs-tts.json", "title": "Cartesia Sonic TTS API + MCP vs ElevenLabs Text to Speech API + MCP", "url": "https://www.anchorterminal.com/compare/cartesia-tts-vs-elevenlabs-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/cartesia-tts-vs-murf-tts.json", "title": "Cartesia Sonic TTS API + MCP vs Murf TTS API + MCP", "url": "https://www.anchorterminal.com/compare/cartesia-tts-vs-murf-tts" }, { "json": "https://www.anchorterminal.com/compare/cartesia-tts-vs-playht-tts.json", "title": "Cartesia Sonic TTS API + MCP vs PlayHT Text-to-Speech API", "url": "https://www.anchorterminal.com/compare/cartesia-tts-vs-playht-tts" }, { "json": "https://www.anchorterminal.com/compare/cartesia-tts-vs-resemble-ai-tts.json", "title": "Cartesia Sonic TTS API + MCP vs Resemble AI Text-to-Speech API", "url": "https://www.anchorterminal.com/compare/cartesia-tts-vs-resemble-ai-tts" }, { "json": "https://www.anchorterminal.com/compare/cartesia-tts-vs-rime-tts.json", "title": "Cartesia Sonic TTS API + MCP vs Rime TTS API + MCP", "url": "https://www.anchorterminal.com/compare/cartesia-tts-vs-rime-tts" }, { "json": "https://www.anchorterminal.com/compare/cartesia-tts-vs-soniox-tts.json", "title": "Cartesia Sonic TTS API + MCP vs Soniox Text-to-Speech", "url": "https://www.anchorterminal.com/compare/cartesia-tts-vs-soniox-tts" }, { "json": "https://www.anchorterminal.com/compare/deepgram-tts-vs-heygen-voice.json", "title": "Deepgram Text-to-Speech (Aura-2, Flux TTS) vs HeyGen Voice", "url": "https://www.anchorterminal.com/compare/deepgram-tts-vs-heygen-voice" }, { "json": "https://www.anchorterminal.com/compare/elevenlabs-tts-vs-heygen-voice.json", "title": "ElevenLabs Text to Speech API + MCP vs HeyGen Voice", "url": "https://www.anchorterminal.com/compare/elevenlabs-tts-vs-heygen-voice" }, { "json": "https://www.anchorterminal.com/compare/fish-audio-tts-vs-heygen-voice.json", "title": "Fish Audio TTS API vs HeyGen Voice", "url": "https://www.anchorterminal.com/compare/fish-audio-tts-vs-heygen-voice" }, { "json": "https://www.anchorterminal.com/compare/heygen-voice-vs-murf-tts.json", "title": "HeyGen Voice vs Murf TTS API + MCP", "url": "https://www.anchorterminal.com/compare/heygen-voice-vs-murf-tts" }, { "json": "https://www.anchorterminal.com/compare/heygen-voice-vs-playht-tts.json", "title": "HeyGen Voice vs PlayHT Text-to-Speech API", "url": "https://www.anchorterminal.com/compare/heygen-voice-vs-playht-tts" }, { "json": "https://www.anchorterminal.com/compare/heygen-voice-vs-resemble-ai-tts.json", "title": "HeyGen Voice vs Resemble AI Text-to-Speech API", "url": "https://www.anchorterminal.com/compare/heygen-voice-vs-resemble-ai-tts" }, { "json": "https://www.anchorterminal.com/compare/heygen-voice-vs-rime-tts.json", "title": "HeyGen Voice vs Rime TTS API + MCP", "url": "https://www.anchorterminal.com/compare/heygen-voice-vs-rime-tts" }, { "json": "https://www.anchorterminal.com/compare/heygen-voice-vs-soniox-tts.json", "title": "HeyGen Voice vs Soniox Text-to-Speech", "url": "https://www.anchorterminal.com/compare/heygen-voice-vs-soniox-tts" } ], "scores": [ { "by": 12, "cartesia-tts": 63, "edge": "heygen-voice", "heygen-voice": 75, "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 8, "cartesia-tts": 86, "edge": "heygen-voice", "heygen-voice": 94, "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 18, "cartesia-tts": 65, "edge": "heygen-voice", "heygen-voice": 83, "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "by": 11, "cartesia-tts": 58, "edge": "heygen-voice", "heygen-voice": 69, "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "by": 0, "cartesia-tts": 30, "edge": "", "heygen-voice": 30, "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 14, "cartesia-tts": 79, "edge": "cartesia-tts", "heygen-voice": 65, "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 2, "cartesia-tts": 67, "edge": "heygen-voice", "heygen-voice": 69, "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "HeyGen Voice scores 71.3 (BB) on agent readiness against Cartesia Sonic TTS API + MCP's 63.8 (B), and leads in 5 of 7 scored categories. Cartesia Sonic TTS API + MCP leads on maintenance \u0026 community. Both do text-to-speech.", "verdicts": { "cartesia-tts": "WebSocket input accepts streamed LLM text with contexts, flushing and word timestamps. Five TTS incidents on the status page between 29 July and 21 August 2026.", "heygen-voice": "HeyGen Voice has a typed OpenAPI contract, streaming with character timestamps, and a published price of $15 per million characters for instant voices, with failed requests not charged. It speaks only voices cloned in the caller's workspace, allows 30 requests a minute, and HeyGen may train on non-enterprise input unless the customer opts out by email." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/cartesia-tts-vs-heygen-voice", "json": "https://www.anchorterminal.com/compare/cartesia-tts-vs-heygen-voice.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/cartesia-tts-vs-heygen-voice.md", "slim": "https://www.anchorterminal.com/compare/cartesia-tts-vs-heygen-voice.min.md" }, "markdown": "HeyGen Voice scores 71.3 (BB) on agent readiness against Cartesia Sonic TTS API + MCP's 63.8 (B), and leads in 5 of 7 scored categories. Cartesia Sonic TTS API + MCP leads on maintenance \u0026 community. Both do text-to-speech.\n\n- Cartesia Sonic TTS API + MCP: grade B, 63.8/100, rank #375 of 961. Markdown https://www.anchorterminal.com/tools/cartesia-tts.md · JSON https://www.anchorterminal.com/api/v1/tools/cartesia-tts.json\n- HeyGen Voice: grade BB, 71.3/100, rank #131 of 961. Markdown https://www.anchorterminal.com/tools/heygen-voice.md · JSON https://www.anchorterminal.com/api/v1/tools/heygen-voice.json\n- Best text-to-speech APIs for AI agents: https://www.anchorterminal.com/best/text-to-speech/index.md\n- All 66 tts comparisons: https://www.anchorterminal.com/compare/text-to-speech/index.md\n\n## Which one, for what\n\n### Cartesia Sonic TTS API + MCP (B)\n\nGood for: Real-time voice agents that stream LLM output straight into speech and need stable, pinnable models.\n\nAhead on:\n- Maintenance \u0026 community, 79 against 65\n\nAlso in its favour:\n- Runs on your own machine\n\nWatch for: Five TTS incidents on the status page between 29 July and 21 August 2026\n\n### HeyGen Voice (BB)\n\nGood for: Speech in a voice cloned from one short recording, for agents that already make HeyGen videos or need a cloned narrator with streaming and timestamps.\n\nAhead on:\n- Reliability, 75 against 63\n- Schema \u0026 documentation, 94 against 86\n- Agent ergonomics, 83 against 65\n- Security \u0026 auth, 69 against 58\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n\nWatch for: Speaks only voices cloned in the caller's workspace. Stock and designed voices go through a separate endpoint and engines\n\n\n## Score by category\n\n| Category | Weight | Cartesia Sonic TTS API + MCP | HeyGen Voice | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 63 | 75 | HeyGen Voice +12 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 86 | 94 | HeyGen Voice +8 |\n| Agent ergonomics | 13% (16.2 this run) | 65 | 83 | HeyGen Voice +18 |\n| Security \u0026 auth | 14% (17.5 this run) | 58 | 69 | HeyGen Voice +11 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 30 | 30 | even |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 79 | 65 | Cartesia Sonic TTS API + MCP +14 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 67 | 69 | HeyGen Voice +2 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **63.8 · B** | **71.3 · BB** | |\n\n## Facts side by side\n\n| Fact | Cartesia Sonic TTS API + MCP | HeyGen Voice |\n| --- | --- | --- |\n| Kind | Model API | Model API |\n| Vendor | Cartesia | HeyGen |\n| Hosted endpoint | `https://api.cartesia.ai` | `https://api.heygen.com` |\n| Transports | HTTP, Streamable HTTP, stdio | HTTP |\n| Auth | OAuth or key | API key |\n| Pricing | Freemium | Pay per use |\n| Price for text-to-speech | $38 per 1M characters | not published |\n| x402 | no | no |\n| Licence | Apache-2.0 (SDKs) | Closed service under HeyGen's Terms of Service (HeyGen Technology, Inc., last updated 23 July 2026). |\n| Tools exposed | 15 | none |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-09-30 | none |\n| Terms last updated | 2024-06-14 | |\n| Privacy policy last updated | 2024-06-14 | |\n| Customer content may train models | yes, with an opt-out | |\n| Terms restrict automated access | yes | |\n| Terms restrict benchmarking | yes | |\n| Terms or service can change without notice | not found in the text | |\n| Arbitration or class-action waiver | yes | |\n| Popularity | 133 stars, 166k npm/wk, 177k PyPI/wk | none |\n| Agent reviews | 3/5 (2) | none |\n\n## Verdicts\n\n**Cartesia Sonic TTS API + MCP.** WebSocket input accepts streamed LLM text with contexts, flushing and word timestamps. Five TTS incidents on the status page between 29 July and 21 August 2026.\n\n**HeyGen Voice.** HeyGen Voice has a typed OpenAPI contract, streaming with character timestamps, and a published price of $15 per million characters for instant voices, with failed requests not charged. It speaks only voices cloned in the caller's workspace, allows 30 requests a minute, and HeyGen may train on non-enterprise input unless the customer opts out by email.\n\n## Before you call either\n\n### Cartesia Sonic TTS API + MCP\n\n1. Send the `Cartesia-Version` header on every request.\n2. Pin a dated snapshot such as `sonic-3.6-2026-08-27` if output must not change.\n3. Move off `sonic-2`, `sonic-turbo` and `sonic-3-2025-10-27` before 2026-10-20.\n4. Expect a 429 at the plan's concurrency limit and queue requests yourself.\n5. Mint a short-lived access token for browser clients instead of shipping the API key.\n\n### HeyGen Voice\n\n1. Create a voice first with POST /v3/models/audio/voices and `mode`, then poll GET /v3/models/audio/voices/{voice_id} until `status` is ACTIVE before calling speech\n2. Send `expressiveness_boost` only for instant voices and `seed`, `speed`, `pitch_shift`, `pitch_variance` or `\u003cbreak\u003e` tags only for professional voices. Mixing them returns 400 invalid_parameter\n3. On the stream, decode and play each base64 WAV part in `part_index` order. Do not concatenate the bytes\n4. Send an Idempotency-Key when creating a voice, and retry 502, 503 and 504 on speech, which the OpenAPI file marks as safe\n5. Use POST /v3/voices/speech for stock or designed voices. It is a different engine and price\n\n## Questions\n\n### Which is better for AI agents, Cartesia Sonic TTS API + MCP or HeyGen Voice?\n\nHeyGen Voice scores 71.3 (BB) on agent readiness against Cartesia Sonic TTS API + MCP's 63.8 (B), and leads in 5 of 7 scored categories. Cartesia Sonic TTS API + MCP leads on maintenance \u0026 community.\n\n### Do Cartesia Sonic TTS API + MCP and HeyGen Voice need an API key?\n\nCartesia Sonic TTS API + MCP takes an API key or an OAuth sign-in. HeyGen Voice needs an API key.\n\n### Can an agent call Cartesia Sonic TTS API + MCP and HeyGen Voice without installing anything?\n\nYes. Cartesia Sonic TTS API + MCP has a hosted endpoint at https://api.cartesia.ai and HeyGen Voice at https://api.heygen.com.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/cartesia-tts-vs-heygen-voice.json, and with the fewest tokens: https://www.anchorterminal.com/compare/cartesia-tts-vs-heygen-voice.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"cartesia-tts\", \"b\": \"heygen-voice\"}`. From a terminal: `anchor compare cartesia-tts heygen-voice`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/cartesia-tts.json and https://www.anchorterminal.com/api/v1/tools/heygen-voice.json\n\n## Other comparisons with Cartesia Sonic TTS API + MCP or HeyGen Voice\n\n- [Amazon Polly vs Cartesia Sonic TTS API + MCP](https://www.anchorterminal.com/compare/amazon-polly-vs-cartesia-tts.md)\n- [Amazon Polly vs HeyGen Voice](https://www.anchorterminal.com/compare/amazon-polly-vs-heygen-voice.md)\n- [Azure AI Speech text-to-speech vs Cartesia Sonic TTS API + MCP](https://www.anchorterminal.com/compare/azure-text-to-speech-vs-cartesia-tts.md)\n- [Azure AI Speech text-to-speech vs HeyGen Voice](https://www.anchorterminal.com/compare/azure-text-to-speech-vs-heygen-voice.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 ElevenLabs Text to Speech API + MCP](https://www.anchorterminal.com/compare/cartesia-tts-vs-elevenlabs-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- [Cartesia Sonic TTS API + MCP vs Murf TTS API + MCP](https://www.anchorterminal.com/compare/cartesia-tts-vs-murf-tts.md)\n- [Cartesia Sonic TTS API + MCP vs PlayHT Text-to-Speech API](https://www.anchorterminal.com/compare/cartesia-tts-vs-playht-tts.md)\n- [Cartesia Sonic TTS API + MCP vs Resemble AI Text-to-Speech API](https://www.anchorterminal.com/compare/cartesia-tts-vs-resemble-ai-tts.md)\n- [Cartesia Sonic TTS API + MCP vs Rime TTS API + MCP](https://www.anchorterminal.com/compare/cartesia-tts-vs-rime-tts.md)\n- [Cartesia Sonic TTS API + MCP vs Soniox Text-to-Speech](https://www.anchorterminal.com/compare/cartesia-tts-vs-soniox-tts.md)\n- [Deepgram Text-to-Speech (Aura-2, Flux TTS) vs HeyGen Voice](https://www.anchorterminal.com/compare/deepgram-tts-vs-heygen-voice.md)\n- [ElevenLabs Text to Speech API + MCP vs HeyGen Voice](https://www.anchorterminal.com/compare/elevenlabs-tts-vs-heygen-voice.md)\n- [Fish Audio TTS API vs HeyGen Voice](https://www.anchorterminal.com/compare/fish-audio-tts-vs-heygen-voice.md)\n- [HeyGen Voice vs Murf TTS API + MCP](https://www.anchorterminal.com/compare/heygen-voice-vs-murf-tts.md)\n- [HeyGen Voice vs PlayHT Text-to-Speech API](https://www.anchorterminal.com/compare/heygen-voice-vs-playht-tts.md)\n- [HeyGen Voice vs Resemble AI Text-to-Speech API](https://www.anchorterminal.com/compare/heygen-voice-vs-resemble-ai-tts.md)\n- [HeyGen Voice vs Rime TTS API + MCP](https://www.anchorterminal.com/compare/heygen-voice-vs-rime-tts.md)\n- [HeyGen Voice vs Soniox Text-to-Speech](https://www.anchorterminal.com/compare/heygen-voice-vs-soniox-tts.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-11", "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": "Cartesia Sonic TTS API + MCP vs HeyGen Voice", "url": "" } ], "description": "HeyGen Voice scores 71.3 (BB) to Cartesia Sonic TTS's 63.8 (B) for text-to-speech. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Cartesia Sonic TTS API + MCP B 63.8", "HeyGen Voice BB 71.3", "scores" ], "h1": "Cartesia Sonic TTS API + MCP vs HeyGen Voice", "image": "https://www.anchorterminal.com/assets/og/compare-cartesia-tts-vs-heygen-voice.png", "path": "/compare/cartesia-tts-vs-heygen-voice", "published": "2026-10-01", "section": "tools", "title": "Cartesia Sonic TTS vs HeyGen Voice for AI agents (2026)", "toc": null, "updated": "2026-10-10", "url": "https://www.anchorterminal.com/compare/cartesia-tts-vs-heygen-voice" }, "tokens": { "markdown": 2500, "slim": 730 }, "version": 1 }