Api
Audio Generation API
Text-to-speech and sound-effect generation with POST /api/v1/speech and POST /api/v1/sound-effects.
Audio renders synchronously: responses usually already carry status: "success" and the result URL in data.taskUrls. The returned data.id still works with GET /api/v1/tasks/{taskId} for a uniform polling flow.
List voices
GET /api/v1/voices returns the available text-to-speech voices and the per-generation credit cost. No request body.
curl -H "Authorization: Bearer $VIDRUSH_API_KEY" \
https://vidrush-ai.com/api/v1/voicesEach voice includes id, name, gender, accent, language, and recommended_model. Use a voice id as voice_id when creating speech.
Text to speech
POST /api/v1/speech converts text to speech with a selected voice.
| Field | Required | Type | Description |
|---|---|---|---|
text | Yes | string | Non-empty text to speak |
voice_id | Yes | string | A voice id from GET /api/v1/voices |
options | No | object | model_id, speed (0.25–4), stability (0–1), similarity_boost (0–1) |
curl -X POST https://vidrush-ai.com/api/v1/speech \
-H "Authorization: Bearer $VIDRUSH_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"text": "Welcome to Vidrush.",
"voice_id": "EXAVITQu4vr4xnSDxMaL",
"options": { "speed": 1.0 }
}'Sound effects
POST /api/v1/sound-effects generates a sound effect from a text prompt.
| Field | Required | Type | Description |
|---|---|---|---|
prompt | Yes | string | Non-empty description of the sound |
options | No | object | duration_seconds (0.5–22), prompt_influence (0–1) |
curl -X POST https://vidrush-ai.com/api/v1/sound-effects \
-H "Authorization: Bearer $VIDRUSH_API_KEY" \
-H "Content-Type: application/json" \
-d '{ "prompt": "A distant rolling thunder clap", "options": { "duration_seconds": 5 } }'Successful response
{
"code": 0,
"message": "ok",
"data": {
"id": "task_123",
"status": "success",
"costCredits": 1,
"taskUrls": ["https://.../audio.mp3"]
}
}