Skip to main content
POST
Text to Speech

Request

Body parameters

string
required
TTS model ID. Options: canopylabs/orpheus-v1-english, canopylabs/orpheus-arabic-saudi, playai-tts, playai-tts-arabic, sarvam-tts.
string
required
The text to synthesize into speech.
string
Voice ID or name. Available voices depend on the model.
string
Language code for Sarvam models (e.g. "hi-IN", "en-IN").
integer
Audio sample rate in Hz (Sarvam models).
number
Speech pace/speed (Sarvam models).

Examples


Response

Returns binary audio data (audio/wav). Save the response body directly to a file.

Pricing