v4
latestOpenAPI 3.1.02026-08-08221179273.1 KBtts
Text To Speech Streaming
Convert text to speech using OpenAI TTS and stream the audio as MP3.
Args: text: Text to convert (query parameter) voice: Optional voice override (VOICE_1, VOICE_2, etc) current_user: Authenticated user
Returns: StreamingResponse with MP3 audio data
get/api/tts.mp3
Query parameters
textstring required
Text to convert to speech (max 400 words)
Text to convert to speech (max 400 words)
voicestring
Voice override (VOICE_1, VOICE_2, etc). If not provided, uses user's preferred voice
Voice override (VOICE_1, VOICE_2, etc). If not provided, uses user's preferred voice
Headers
x-user-idstring nullable
Response
Successful Response
{"stackTrail":"paths:/api/tts.mp3:get:responses:200:content:application/json:schema","oasType":"schema","type":"unknown"}