Convert text to speech audio using the OpenDunes API from Go.
The text-to-speech endpoint converts written text into natural-sounding audio. Voices and models that support Arabic and French are available for Algerian and broader North African deployments.
The response body is the raw audio stream. Write it directly to a file or buffer for playback.
| Parameter | Description |
|---|---|
model | TTS model slug |
input | Text to synthesize (max 4096 characters) |
voice | Voice name (model-dependent) |
response_format | mp3 (default), opus, aac, flac |
speed | Playback rate multiplier (0.25–4.0) |
TTS is billed per 1,000 characters of input at the model's DA rate.