Skip to main content
Documentation Navigation

Resources

Voice Generation

Convert text to natural-sounding speech. Voice selection, speed control, streaming, and a pronunciation dictionary.

FairStack offers 10 voice models with 168+ preset voices, from budget TTS to premium ElevenLabs quality.

Basic TTS

curl -X POST https://api.fairstack.ai/v1/generations/voice \
  -H "Authorization: Bearer $FAIRSTACK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "fish-s2.1-pro", "input": {"text": "Hello world", "voice": "933563129e564b19a115bedd57b7406a"}}'

Voice selection

List available voices:

curl https://api.fairstack.ai/v1/voices

Voices vary by model. FairStack Voice v1 and IndexTTS2 support zero-shot voice cloning. ElevenLabs has its own voice library.

Speed and format

Control speech speed (0.5x to 2.0x) and output format (mp3, wav, ogg):

{
  "model": "elevenlabs-turbo-2-5",
  "input": {
    "text": "Speak slowly and clearly",
    "voice": "nPczCjzI2devNBz1zQrb",
    "speed": 0.8,
    "format": "mp3"
  }
}

Next steps

Video Generation Voice Cloning