ByteDance · AUDIO

Sound Effects API

Generate a sound effect from a text description (e.g. "sword unsheathing", "8-bit coin pickup"). Optional targetDuration (1-120s, default 3). Async: returns a jobId — poll GET /api/v1/jobs/:id until it succeeds, then read result.audio.

Available through Sorceress API

Use with an AI agentManage API keys

Using Sound Effects in your workflow

Sorceress brings ByteDance models into a shared API catalog. Select this model explicitly, check its supported inputs, and keep your API key on your server. Model capabilities differ; the schema and options on this page describe this entry rather than every model from the same brand.

  • Add sound or speech to a creative workflow.
  • Integrate audio generation with your application using the model-specific parameters.

Pricing and availability

seed-audio: 1 credit per second of finished audio (min 1). suno-sounds: flat 2 credits. Charged only on success.. Successful work is billed in Sorceress credits. Defaults and optional inputs can affect the total.

Inputs and supported options

promptstring · required

Description of the sound effect (e.g. "heavy wooden door creaking open"). Max 1800 chars (500 for suno-sounds).

modelstring · optional

"seed-audio" (default, 1 credit/second, controllable length) or "suno-sounds" (flat 2 credits, any length, supports seamless looping).

targetDurationnumber · optional

seed-audio only: approximate length in seconds (1-120). Default 3. You are billed 1 credit per second of finished audio.

loopboolean · optional

suno-sounds only: match the head and tail so the sound can repeat seamlessly. Ideal for ambience and engine loops.

API request template

Replace placeholders and choose valid values from the input contract. 

POST /api/v1/tools/sfx_generate
Authorization: Bearer $SORCERESS_API_KEY
Content-Type: application/json

{
  "prompt": "<prompt>"
}
Read the endpoint reference →

Completion, results and billing

Save the job identifier returned by asynchronous requests and poll the jobs endpoint until the job succeeds or fails. Do not resubmit a generation just because it is still processing. Chat returns a completed reply and usage details. A multi-step workflow can include separately billed successful steps even if a later step fails. Keep returned asset links with your project, and consult each action for its output format.

Coding agents can discover the current catalog and input requirements from the Sorceress agent instructions. Use a Sorceress key; provider credentials stay on the server.