Skip to main content

Text to Speech

Convert text into spoken audio. Use this to add voice to your application — narrate content, build voice interfaces, or generate audio for accessibility features.

POST 
/v1/audio/speech

Synthesize natural-sounding speech from text. The response body is a binary audio stream in the format you specify.

curl -X POST https://inference.wiline.com/v1/audio/speech \
  -H "Authorization: Bearer $WEC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"tts-1","input":"Hello world","voice":"nova","response_format":"mp3"}' \
  --output speech.mp3

Request​

Responses​

The synthesized audio file. Content-Type varies by response_format: audio/mpeg for mp3, audio/opus, audio/aac, audio/flac, audio/wav, or audio/pcm.