Suno Speech API reference
Check Suno Speech availability, inputs, parameters, file requirements, credit pricing, and request examples for Rivya Public API v1. Model ID: suno-speech.
suno-speech
text
Not required for the minimal request
Credit rate: 12 per request The final cost is rounded up to whole credits.
Audio
FIXED
5000 characters
Request fields
Set model at the top level. Put model-specific controls and reference inputs in params, using the format documented for this model.
| Key | Type | Required | Default | Description |
|---|---|---|---|---|
| model | string | Yes | suno-speech | Set model to suno-speech. |
| prompt | string | Yes | - | Maximum 5000 characters for this model. |
| params | object | No | - | The model-specific params object. Use the documented keys and reference-file format for this model. |
| client_request_id | string | No | - | Optional ID for tracing this request in your system. It does not replace Idempotency-Key. |
Model parameters
| Key | Type | Required | Default | Range | Options | Description |
|---|---|---|---|---|---|---|
| customMode | select | No | false | - | false, true | Mode |
| tone | text | No | - | - | - | Tone and delivery |
| variety | number | No | - | min 0 / max 4 / step 1 | - | Variety |
| vocalGender | select | No | f | - | f, m | Vocal gender |
| backgroundMusic | select | No | false | - | false, true | Background music |
Minimal request
{
"model": "suno-speech",
"prompt": "Welcome. Here is a quick introduction to the product.",
"params": {
"customMode": "false"
}
}Example response
An accepted generation request returns a task ID. Poll the status endpoint until the task succeeds or fails. A status request failure does not mean generation failed.
{
"id": "task_suno_speech_example",
"status": "queued",
"model": "suno-speech",
"reserved_credits": 12,
"final_credits": 0,
"settlement_status": "RESERVED",
"created_at": "2026-05-11T00:00:00.000Z",
"updated_at": "2026-05-11T00:00:00.000Z",
"result": null,
"error": null
}Common errors
validation_failed, insufficient_credits, idempotency_conflict, rate_limited, not_found
An accepted generation request returns a task ID. Poll the status endpoint until the task succeeds or fails. A status request failure does not mean generation failed.
