Seed Audio 2.0 API Documentation

Base URL

https://api.seedaudio.co/v2

Authentication

Create an API key from your account settings. Send it as a Bearer token with every request.

Authorization: Bearer YOUR_API_KEY

Billing

• Web and API requests use the same credit wallet.
• Audio is billed at 5 credits per generated minute, calculated from actual output duration.
• The minimum charge for a completed generation is 5 credits.
• Credits are reserved before generation; unused credits are returned after success.
• Failed tasks receive a full refund of their reservation.

Create a generation

POST /audio/generations

curl -X POST 'https://api.seedaudio.co/v2/audio/generations' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  -H 'Idempotency-Key: seed-audio-request-001' \
  -d '{
    "model": "seed-audio-2.0",
    "prompt": "Create a cinematic midnight radio scene with two quiet speakers, soft rain, distant traffic, and a restrained ambient score.",
    "output_format": "mp3",
    "sample_rate": 24000,
    "speed": 1,
    "volume": 1,
    "pitch": 0
  }'

Successful submission returns HTTP 202:

{
  "id": "audio_task_xxx",
  "object": "audio.generation",
  "model": "seed-audio-2.0",
  "status": "processing",
  "billing": { "reserved_credits": 5 },
  "output": null,
  "usage": null,
  "error": null
}

Request fields

Query task status

GET /audio/generations/{task_id}

curl 'https://api.seedaudio.co/v2/audio/generations/audio_task_xxx' \
  -H 'Authorization: Bearer YOUR_API_KEY'

Poll every 3–5 seconds. A successful task returns:

{
  "id": "audio_task_xxx",
  "object": "audio.generation",
  "model": "seed-audio-2.0",
  "status": "succeeded",
  "output": {
    "url": "https://cdn.seedaudio.co/v2/output.mp3",
    "duration_seconds": 43.2,
    "format": "mp3"
  },
  "usage": { "credits": 5 },
  "error": null
}

Possible statuses are queued, processing, succeeded, failed, and canceled.

JavaScript example

const headers = {
  Authorization: `Bearer ${process.env.SEED_AUDIO_API_KEY}`,
  "Content-Type": "application/json",
  "Idempotency-Key": crypto.randomUUID(),
};

const created = await fetch("https://api.seedaudio.co/v2/audio/generations", {
  method: "POST",
  headers,
  body: JSON.stringify({
    model: "seed-audio-2.0",
    prompt: "Build a cinematic city sound scene after midnight.",
    output_format: "mp3",
  }),
}).then((response) => response.json());

const task = await fetch(
  `https://api.seedaudio.co/v2/audio/generations/${created.id}`,
  { headers: { Authorization: headers.Authorization } }
).then((response) => response.json());

Python example

import os
import uuid
import requests

base_url = "https://api.seedaudio.co/v2"
headers = {
    "Authorization": f"Bearer {os.environ['SEED_AUDIO_API_KEY']}",
    "Idempotency-Key": str(uuid.uuid4()),
}

created = requests.post(
    f"{base_url}/audio/generations",
    headers=headers,
    json={
        "model": "seed-audio-2.0",
        "prompt": "Create a layered documentary sound scene.",
        "output_format": "mp3",
    },
).json()

task = requests.get(
    f"{base_url}/audio/generations/{created['id']}",
    headers={"Authorization": headers["Authorization"]},
).json()

Errors

Errors use real HTTP status codes and a consistent response body.

{
  "error": {
    "code": "insufficient_credits",
    "message": "At least 5 credits are required",
    "request_id": "request_xxx"
  }
}