OpenAI · Vision & Audio

OpenAI Voice & Whisper Live

Turn text into speech with selectable voices, or transcribe an audio file URL with Whisper.

Endpoints

POST/v1/openai/audio/speech— Synthesize speech audio from text.

POSTapi.apirunner.dev/v1/openai/audio/speech

idle

0 ms

Press Run to send the request.

curl -X POST "https://api.apirunner.dev/v1/openai/audio/speech" \
  -H "Authorization: Bearer YOUR_RUNNER_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tts-1",
    "voice": "alloy",
    "input": "Your build passed. Deploying to production.",
    "format": "mp3"
  }'

Parameters

Name	In	Type	Default	Notes
model	body	tts-1 \| tts-1-hd	tts-1	—
voice	body	alloy \| echo \| nova \| shimmer	alloy	—
inputrequired	body	string	Your build passed. Deploying to production.	—
format	body	mp3 \| wav \| opus	mp3	—