# Seed Audio 1.0 API

> Speech and audio generator driven by text, up to 3 reference audio clips or one image, with pitch and speed controls

Synthesizes audio from a prompt of up to 2048 characters. A preset or cloned `voice` can be chosen, and up to 3 reference clips can be cited in the prompt as @Audio1 to @Audio3; a single reference image works instead, but not together with audio. Output is wav, mp3, pcm or ogg_opus at sample rates from 8000 to 48000 Hz. Speed and volume range 0.5 to 2, pitch shifts -12 to 12 semitones, and `multilingual` switches to a variant for mixed-language text.

- Model id: `bytedance/seed-audio-1.0`
- Made by: ByteDance
- Category: Audio
- Output: audio
- Charged by usage (up to $0.154 per run, typical $0.023; the rest of the hold is refunded): $0.1875 / minute of generated audio (cheapest run $0.023 (23 API credits))
- Run: `POST https://api.doitong.com/v1/run/bytedance/seed-audio-1.0`
- Quote: `POST https://api.doitong.com/v1/quote/bytedance/seed-audio-1.0`
- Docs page: https://doitong.com/developers/models/bytedance/seed-audio-1.0

## Pricing

Price: **$0.1875 / minute of generated audio**. Charged by actual usage at $0.1875 / minute of generated audio: up to $0.154 per run (the quote gives the maximum for your input), the rest is refunded automatically after the run. A typical run costs $0.023.

The full example input below holds up to $0.154 = 154 API credits (up to 0.8167 min of generated audio × $0.1875) when it starts; a typical run costs $0.023 (23 API credits).

Prices are the upstream price in USD, paid from the API balance in API credits (1000 API credits = 1 USD). This model is charged by usage: `POST https://api.doitong.com/v1/quote/bytedance/seed-audio-1.0` with the same JSON body returns the most the run can cost for that input (`credits`, debited when the run starts); after the run you pay the usage the model reports and the rest is refunded automatically. An input whose maximum would exceed the per-run limit is refused with 422. Invalid input is never charged and failed or canceled requests are refunded automatically.

## Input parameters

Send either the canonical name or the native field name (not both). Canonical names are the same across models.

| Parameter | Canonical name | Type | Required | Default | Allowed values / range | Description |
|---|---|---|---|---|---|---|
| `prompt` |  | string | yes |  | ≤ 2048 characters | Synthesis prompt or text, with ordered audio references expressed as @Audio1 for the first input, @Audio2 for the second, and @Audio3 for the third. |
| `voice` |  | string \| null | no |  |  | Select a synthesis voice by supplying either its preset name or, for a cloned voice, its ID. |
| `audio_urls` | `audios` | array of audio URL | no |  | ≤ 3 items | Supply reference audio through at most 3 URLs, with each file in wav/mp3/pcm/ogg_opus format and limited to 10 MB and 30 seconds. In the prompt, identify the clips with @Audio1, @Audio2, @Audio3. |
| `image_url` | `image` | string (image URL) \| null | no |  |  | Provide one image reference by URL only when no audio references are supplied. The image must be jpeg/png/webp and no larger than 10 MB. |
| `output_format` |  | enum (string) | no | `mp3` | `wav`, `mp3`, `pcm`, `ogg_opus` | Format for the generated audio. |
| `sample_rate` |  | enum (integer) | no | `24000` | `8000`, `16000`, `24000`, `32000`, `44100`, `48000` | Sampling frequency in Hz for the output audio. |
| `speed` |  | number | no | `1` | 0.5 – 2 | Speech rate multiplier: 1.0 gives normal speed, 0.5 gives half speed, and 2.0 gives twice the speed. |
| `volume` |  | number | no | `1` | 0.5 – 2 | Volume multiplier: 1.0 gives normal volume, 0.5 gives half the volume, and 2.0 gives twice the volume. |
| `pitch` |  | integer | no | `0` | -12 – 12 | Pitch adjustment for the voice, measured in semitones: 0 leaves pitch unchanged, -12 shifts it down an octave, and 12 shifts it up an octave. |
| `multilingual` |  | boolean | no | `false` |  | Model variant selection: enabling the multilingual variant improves handling when prompts mix languages or use a language other than English. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Screening can be relaxed by setting false, provided the caller is authorized. |

File parameters (`audios`, `image`) take a public `https://` URL, a `data:` URI up to 10 MB, or the `file_url` of an upload from `POST /files`.

## Example input

Required parameters only:

```json
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}
```

A fuller example:

```json
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}
```

## Run it

Set `DOITONG_API_KEY` to a key from https://doitong.com/developers/dashboard#keys. `?wait=20` returns the finished request in the same call when it is ready within 20 seconds; otherwise poll `GET /requests/{id}` (it also accepts `?wait=`), or pass `webhook_url`.

### curl

```bash
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/bytedance/seed-audio-1.0?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"
```

### JavaScript

```javascript
const API = "https://api.doitong.com/v1";
const headers = {
  "Authorization": "Bearer " + process.env.DOITONG_API_KEY,
  "Content-Type": "application/json",
};

// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/bytedance/seed-audio-1.0?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);

// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
  res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
  request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
```

### Python

```python
import os
import requests

API = "https://api.doitong.com/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/bytedance/seed-audio-1.0", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
    raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])

# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
    request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
    raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])
```

### MCP

The MCP server at `https://api.doitong.com/v1/mcp` exposes the tools `search_models`, `get_model`, `quote`, `run`, `get_request`, `cancel_request`, `list_requests`, `create_upload` and `get_account`. A `run` call for this model:

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "run",
    "arguments": {
      "model_id": "bytedance/seed-audio-1.0",
      "input": {
        "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
      },
      "wait_seconds": 20
    }
  }
}
```

## Response

Every call returns a request object. `status` is one of `queued`, `running`, `succeeded`, `failed`, `canceled`. `outputs` lists the generated files with URLs on our storage (kept forever, or 7 days with `?storage=temporary`; `storage` says which); `output` is the model's own result object with the same URLs.

```json
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "bytedance/seed-audio-1.0",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 154,
    "usd": "0.154",
    "charged": 154,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  },
  "output": {
    "audio": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp3",
      "content_type": "audio/mpeg",
      "file_name": "0-output.mp3",
      "file_size": 1843200,
      "duration": 5,
      "channels": 1,
      "sample_rate": 1,
      "bitrate": "string"
    }
  },
  "outputs": [
    {
      "type": "audio",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp3",
      "content_type": "audio/mpeg",
      "file_size": 1843200,
      "duration": 12,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `audio` | object {url, content_type, file_name, file_size, duration, channels, sample_rate, bitrate} | Audio file produced by generation. |

## Related models

- [MMAudio V2](https://doitong.com/developers/models/mmaudio-v2.md) (`mmaudio-v2`): $0.001 / second
- [DeepFilterNet 3](https://doitong.com/developers/models/deepfilternet3.md) (`deepfilternet3`): $0.001 / second of input audio
- [Demucs](https://doitong.com/developers/models/demucs.md) (`demucs`): $0.0007 / second of input audio
- [ElevenLabs Audio Isolation](https://doitong.com/developers/models/elevenlabs/audio-isolation.md) (`elevenlabs/audio-isolation`): $0.10 / minute of input file
- [Elevenlabs Sound Effects V2](https://doitong.com/developers/models/elevenlabs/sound-effects/v2.md) (`elevenlabs/sound-effects/v2`): $0.002 / second
- [ElevenLabs Voice Changer](https://doitong.com/developers/models/elevenlabs/voice-changer.md) (`elevenlabs/voice-changer`): $0.30 / minute of input audio
- [FFmpeg API \[Merge Audios\]](https://doitong.com/developers/models/ffmpeg-api/merge-audios.md) (`ffmpeg-api/merge-audios`): $0.00017 / second of processing time
- [Ffmpeg Api · Loudnorm](https://doitong.com/developers/models/ffmpeg-api/loudnorm.md) (`ffmpeg-api/loudnorm`): $0.00017 / second of processing time

## Links

- HTML page: https://doitong.com/developers/models/bytedance/seed-audio-1.0
- All models and guides for AI agents: https://doitong.com/developers/llms.txt
- OpenAPI 3.1 with this model's typed request body: https://doitong.com/developers/openapi.json?model=bytedance/seed-audio-1.0
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/bytedance/seed-audio-1.0