API Documentation

Speech to Text

Transcribe audio to text. Supports 99 languages with auto-detection.

Request Body (multipart/form-data)

Response

{
  "text": "Hello, this is a transcription test.",
  "language": "en",
  "duration": 3.5,
  "segments": [
    {
      "start": 0.0,
      "end": 1.8,
      "text": "Hello, this is",
      "speaker": "SPEAKER_00"
    },
    {
      "start": 1.8,
      "end": 3.5,
      "text": "a transcription test.",
      "speaker": "SPEAKER_00"
    }
  ]
}

Voice Cloning

Generate speech in a cloned voice. Upload a reference audio and text.

Request Body (multipart/form-data)

Response

Returns the audio file as binary data, same as the TTS endpoint.

Voice Changer

Convert audio to sound like a different voice. Upload source audio and choose a target voice.

Request Body (multipart/form-data)

Example Request

curl -X POST https://api.tts.ai/v1/voice-convert/ \
  -H "Authorization: Bearer sk-tts-your-key" \
  -F "file=@source_audio.mp3" \
  -F "target_voice=af_bella" \
  -F "model=openvoice" \
  -o converted.wav

Response

Returns the converted audio file as binary data.

Speech Translation

Translate spoken audio from one language to another. Combines speech-to-text, translation, and text-to-speech in a single call.

Request Body (multipart/form-data)

Response

{
  "original_text": "Hello, how are you?",
  "translated_text": "Hola, como estas?",
  "source_language": "en",
  "target_language": "es",
  "audio_url": "https://api.tts.ai/v1/results/translate_abc123.mp3",
  "credits_used": 5
}

Speech to Speech

Transform speech style, emotion, or delivery while keeping the content. Useful for adjusting tone, pacing, and expressiveness.

Request Body (multipart/form-data)

Response

Returns the transformed audio file as binary data.

Audio Tools

Audio processing endpoints for enhancement, vocal removal, stem splitting, and more.

{
  "key": "C",
  "scale": "Major",
  "bpm": 120.0,
  "time_signature": "4/4",
  "camelot": "8B",
  "compatible_keys": ["C Major", "G Major", "F Major", "A Minor"]
}

Voice Chat

Send audio or text and receive an AI response with synthesized speech.

Request Body (multipart/form-data or JSON)

Response

{
  "conversation_id": "conv_abc123",
  "user_text": "What is the capital of France?",
  "ai_text": "The capital of France is Paris.",
  "audio_url": "https://api.tts.ai/v1/audio/tmp/resp_xyz.mp3",
  "credits_used": 3
}

Batch TTS

Submit multiple texts for parallel TTS generation. Optionally receive a webhook callback when all jobs complete.

Parameters

Response

{
  "batch_id": "abc123",
  "total": 3,
  "completed": 0,
  "status": "processing"
}

Poll progress with GET /v1/tts/batch/result/?batch_id=abc123

Voice Embedding

Pre-compute a voice embedding from reference audio. Use the returned embed_id in subsequent voice cloning requests for near-instant generation.

Parameters

Response

{
  "embed_id": "emb_abc123",
  "model": "chatterbox",
  "duration_ms": 450
}

Health Check

Check GPU server status, loaded models, and queue size. No authentication required. Cached for 30 seconds.

Response

{
  "status": "online",
  "latency_ms": 45,
  "queue_size": 3,
  "models_loaded": ["kokoro", "chatterbox", "cosyvoice2"]
}

List Models

Returns a list of all available models with their capabilities.

Response

{
  "models": [
    {
      "id": "kokoro",
      "name": "Kokoro",
      "type": "tts",
      "tier": "standard",
      "languages": ["en", "ja", "ko", "zh", "fr"],
      "supports_cloning": false,
      "supports_streaming": true,
      "credits_per_1k_chars": 2
    },
    {
      "id": "chatterbox",
      "name": "Chatterbox",
      "type": "tts",
      "tier": "premium",
      "languages": ["en"],
      "supports_cloning": true,
      "supports_streaming": true,
      "credits_per_1k_chars": 4
    }
  ]
}

List Voices

Returns a list of all available voices, optionally filtered by model or language.

Query Parameters

Response

{
  "voices": [
    {
      "id": "af_bella",
      "name": "Bella",
      "model": "kokoro",
      "language": "en",
      "gender": "female",
      "preview_url": "https://api.tts.ai/v1/voices/preview/af_bella.mp3"
    }
  ],
  "total": 142
}

Subtitles (SRT / VTT) new

Generate synchronised subtitles for any completed TTS job. Runs Whisper alignment over the audio and returns SRT or WebVTT. Result is cached on disk so a second call for the same uuid is a disk read.

Query Parameters

curl "https://api.tts.ai/v1/speech/subtitles/?uuid=$UUID&format=srt&download=1" -o subtitles.srt

Pronunciation Dictionary new

Tell the TTS engine how to pronounce specific words. Saved entries auto-apply to every TTS request you make. 200-entry per-account limit.

Request Body (POST)

# Save an entry
curl -X POST https://tts.ai/api/v1/pronunciations/ \
  -H "Authorization: Bearer sk-tts-..." \
  -H "Content-Type: application/json" \
  -d '{"word": "GIF", "replacement": "jiff"}'

# List your entries
curl https://tts.ai/api/v1/pronunciations/ -H "Authorization: Bearer sk-tts-..."

# Delete entry by id
curl -X DELETE "https://tts.ai/api/v1/pronunciations/?id=42" -H "Authorization: Bearer sk-tts-..."

You can also pass per-request overrides without saving them — include pronunciations on any /v1/tts/ call as either an object or an array (see the TTS endpoint params).

Article Narrator new

Drop a single