---
title: "Unified Sound Generate"
method: POST
path: "/v1/sounds/generate"
tags: ["Unified Agent APIs"]
---

# Unified Sound Generate

`POST /v1/sounds/generate`

Generate sound effects or short music tracks from a text prompt.

Distinct from text-to-speech (`/v1/speech/synthesize`): this endpoint does
NOT produce spoken words. It synthesizes raw audio (SFX, ambient, foley,
instrumental music) from a natural language description.

Returns base64-encoded audio bytes plus the format and duration.

## Request body

- SoundGenerateRequest
  - `prompt` string, required
  - `duration_seconds` number
  - `prompt_influence` number
  - `output_format` string
  - `duration` number, nullable

## Response `200`

Successful Response

- unknown

## Other responses

- `422` — Validation Error

---

[API](https://skmtc.net/suprsonic/apis/suprsonic-unified-agent-api.md) · [All operations](https://skmtc.net/suprsonic/apis/suprsonic-unified-agent-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/suprsonic/suprsonic-unified-agent-api/revisions/2a1b6fcb4ef0/schema)