SpeechifyAI Build API

REST endpoints for text-to-speech, streaming, and voice cloning

The SpeechifyAI Build API is a REST API at https://api.speechify.ai. Use it to generate speech from text, stream long-form audio, and clone voices from a short reference sample.

A minimal call. The request and response are generated from the API spec, so they stay in sync with the live endpoint.

POST
/v1/audio/speech
curl -X POST https://api.speechify.ai/v1/audio/speech \
     -H "Authorization: Bearer <token>" \
     -H "Content-Type: application/json" \
     -d '{
  "input": "Hello! This is the Speechify text-to-speech API.",
  "voice_id": "geffen_32",
  "audio_format": "mp3",
  "model": "simba-3.2"
}'
Try it
Response
{
  "audio_data": "example",
  "audio_format": "wav",
  "billable_characters_count": 10,
  "speech_marks": {
    "chunks": [
      {}
    ],
    "end": 1,
    "end_time": 1,
    "start": 1,
    "start_time": 1,
    "type": "example",
    "value": "example"
  }
}

Explore

Text to Speech

Synthesize speech with POST /v1/audio/speech or stream long-form audio with POST /v1/audio/stream. Up to 2,000 characters per synthesis; up to 20,000 for streaming.

Voice

List, create, delete, and preview voices - including clones minted from a 10-30 second sample with the speaker’s verified consent. Cloned voices work across every supported language.

Response format

Non-streaming endpoints return JSON. Speech synthesis returns base64-encoded audio in audio_data. The streaming endpoint returns raw audio chunks via HTTP chunked transfer encoding.

Errors

Every non-2xx response uses the same JSON envelope:

{
  "error": {
    "code": "voice_not_found",
    "message": "Voice 'voice_demo0001' does not exist."
  },
  "request_id": "7f3a2c1b4d5e6f7a"
}

Check error.code in your SDK exception handler - it is a stable, machine-readable identifier you can branch on. error.message is human-friendly and may change between releases. error.fields carries per-field validation errors when relevant, error.details carries structured context a flat field map cannot express, and error.docs_url links the page that resolves the error where one exists (today, the plan-limit 429s). All three are omitted when empty. request_id echoes the Speechify-Request-Id response header; quote it when filing support tickets.

See Get started for authentication and limits, and Idempotency for retry-safe writes.