Text-to-Speech

Generate Text-to-Speech

Generate speech from Arabic text using a specific model. Supports both streaming and non-streaming responses.

post/text-to-speech/{model_id}

Request

model_idstring required

The model identifier to use for generation

voice_idstring required

The voice ID to use for synthesis

textstring required

The Arabic text to convert to speech

stabilitynumber required

Voice stability (0.0 to 1.0). Higher values produce more consistent output

speednumber

Speech speed multiplier (0.7 to 1.2). Values below 1.0 slow down speech, values above 1.0 speed it up

streamingboolean required

If true, returns streaming PCM16 audio. If false, returns complete WAV file

sample_ratenumber

Output sample rate in Hz. Use 48000 for WebRTC-native audio with no client resampling.

dialect'auto' | 'emirati' | 'fusha'

Dialect hint for synthesis.

Audio response (streaming or complete file)