FreeTTS REST API

REST/JSON API for text-to-speech synthesis, audio and SRT subtitle download, and voice listing. Uses x-api-key header auth. Endpoints: POST /api/v1/tts, GET /api/audio/{file_id}, GET /api/srt/{file_id}, GET /api/voices. Submitted 2026-08-28 from shubham@telenow.ai with a NAME ONLY -- no apis.json, no docs URL, no provider. telenow.ai is a HubSpot page unrelated to freetts.org, and nothing on freetts.org links the two, so this is a third-party submission. freetts.org itself is healthy and serves an llms.txt; no apis.json and no OpenAPI resolve. The gate's own research notes the backend proxies Microsoft Azure Neural TTS -- recorded as provenance, not as a policy problem: building a product on Azure TTS is that service's intended use, unlike the model relays refused this week, which documented redirecting first-party CLI clients. Verified 2026-08-28. ENRICHMENT PASS 2026-08-28: contract discovery ran against the API host root, the docs host and every well-known path and found no machine-readable contract. /openapi.json, /swagger.json, /openapi.yaml, /api-docs, /docs and /redoc all return the Next.js catch-all 404; /api/openapi.json, /api/v1/openapi.json, /api/docs, /api/redoc and /api/schema all return the API application's own JSON 404 {"detail":"Not Found"}, so the FastAPI-style app that serves this API has its interactive docs and schema routes disabled. No GraphQL, no MCP endpoint, no agent card, no WSDL, no .proto. The endpoint set is larger than first recorded: POST /api/v1/tts, POST /api/tts-pro (expressive styles, named only in llms.txt, existence confirmed by a live 405 on GET), GET /api/audio/{file_id}, GET /api/srt/{file_id}, GET /api/voices and an undocumented GET /api/health returning 200 {"status":"ok","timestamp":}. GET /api/voices is fully open - it returned 585,024 bytes and 1,410 voice objects with no credential. The /developers hero markets the API as "No Key Required" while the same page's FAQ, all four code samples and the live 401 ({"detail":"Missing x-api-key header"}) require an x-api-key header. Free-tier limits are published at three different values (10, 15 and 20 requests/minute) and the per-request character cap at two (1,000 and 5,000) across two of the provider's own pages, and no rate-limit response headers are emitted at all. The documented embed widget loader https://freetts.org/widget.js returns 404.

Work with this as data

Every API here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for apis

7 MCP tools reach this
  • find_apisBrowse and filter every API in the catalog.
  • get_api_artifactsOne API's artifacts, grouped by type.
  • get_openapiThe primary OpenAPI for this API.
  • find_similar_apisAPIs that look like this one.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This API
curl "https://apis.io/api/v1/apis/freetts-rest-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no email required.

A second provider on the same verified email joins the account you already have.

API entry from apis.yml

apis.yml Raw ↑
name: FreeTTS REST API
description: 'REST/JSON API for text-to-speech synthesis, audio and SRT subtitle download, and voice listing.
  Uses x-api-key header auth. Endpoints: POST /api/v1/tts, GET /api/audio/{file_id}, GET /api/srt/{file_id},
  GET /api/voices.


  Submitted 2026-08-28 from shubham@telenow.ai with a NAME ONLY -- no apis.json, no docs URL, no provider.
  telenow.ai is a HubSpot page unrelated to freetts.org, and nothing on freetts.org links the two, so
  this is a third-party submission. freetts.org itself is healthy and serves an llms.txt; no apis.json
  and no OpenAPI resolve. The gate''s own research notes the backend proxies Microsoft Azure Neural TTS
  -- recorded as provenance, not as a policy problem: building a product on Azure TTS is that service''s
  intended use, unlike the model relays refused this week, which documented redirecting first-party CLI
  clients. Verified 2026-08-28.

  ENRICHMENT PASS 2026-08-28: contract discovery ran against the API host root, the docs host and every
  well-known path and found no machine-readable contract. /openapi.json, /swagger.json, /openapi.yaml,
  /api-docs, /docs and /redoc all return the Next.js catch-all 404; /api/openapi.json, /api/v1/openapi.json,
  /api/docs, /api/redoc and /api/schema all return the API application''s own JSON 404 {"detail":"Not
  Found"}, so the FastAPI-style app that serves this API has its interactive docs and schema routes disabled.
  No GraphQL, no MCP endpoint, no agent card, no WSDL, no .proto. The endpoint set is larger than first
  recorded: POST /api/v1/tts, POST /api/tts-pro (expressive styles, named only in llms.txt, existence
  confirmed by a live 405 on GET), GET /api/audio/{file_id}, GET /api/srt/{file_id}, GET /api/voices and
  an undocumented GET /api/health returning 200 {"status":"ok","timestamp":<epoch>}. GET /api/voices is
  fully open - it returned 585,024 bytes and 1,410 voice objects with no credential. The /developers hero
  markets the API as "No Key Required" while the same page''s FAQ, all four code samples and the live
  401 ({"detail":"Missing x-api-key header"}) require an x-api-key header. Free-tier limits are published
  at three different values (10, 15 and 20 requests/minute) and the per-request character cap at two (1,000
  and 5,000) across two of the provider''s own pages, and no rate-limit response headers are emitted at
  all. The documented embed widget loader https://freetts.org/widget.js returns 404.'
humanURL: https://freetts.org/developers
baseURL: https://freetts.org/api
tags:
- Text-to-Speech
- Speech Synthesis
- AI-voice
- Audio
- Media
- Accessibility
- Speech-to-Text
- Content Creation
- Developer Tools
tags_raw:
- Text-to-Speech
- Speech Synthesis
- AI Voice
- Audio
- Media
- Accessibility
- Speech-to-Text
- Content Creation
- Developer Tools
properties:
- type: Documentation
  url: https://freetts.org/developers
- type: APIReference
  url: https://freetts.org/developers#endpoints
- type: GettingStarted
  url: https://freetts.org/developers#quickstart
- type: LLMsTxt
  url: https://freetts.org/llms.txt
- type: Authentication
  url: authentication/freetts-authentication.yml
- type: ErrorCatalog
  url: errors/freetts-problem-types.yml
- type: RateLimits
  url: rate-limits/freetts-rate-limits.yml
- type: Conventions
  url: conventions/freetts-conventions.yml
- type: DataModel
  url: data-model/freetts-data-model.yml
- type: JSONSchema
  url: json-schema/freetts-voice.json