post
https://platform.perso.ai/api/studio/v1/task/tts/
Create a new Text-to-Speech (TTS) task.
Request Parameters
| Parameter | Required | Description |
|---|---|---|
agent | Yes | Agent identifier |
tts_type | Yes | TTS voice type (e.g., openai-nova) |
tts_audio_format | Yes | Output format (see formats below) |
tts_text | Yes | Array of text strings to convert |
webhook_url | No | URL for completion callback |
tts_gap_start_ms | No | Silence at start (milliseconds) |
tts_gap_during_ms | No | Silence between segments |
tts_gap_end_ms | No | Silence at end |
Audio Formats
| Format | Description |
|---|---|
wav_16bit_32000hz_mono | WAV 16-bit, 32kHz, mono |
mp3_320kbps_mono | MP3 320kbps, mono |
Example
Select "TTSTaskRequestExample" or "TTSTaskRequestExampleWithWebhook" from the Examples dropdown.