---
title: Seed Audio 1.0 | Runware Docs
url: https://runware.ai/docs/models/bytedance-seed-audio-1-0
description: Versatile speech generation model for expressive TTS, voice conversion, and speech editing
---
# Seed Audio 1.0

![Seed Audio 1.0](https://assets.runware.ai/covers/bytedance-seed-audio-1-0.jpg)

Seed Audio 1.0 is a ByteDance speech generation model built for high-quality, highly controllable audio output. Public technical materials describe the underlying Seed-TTS family as supporting zero-shot text-to-speech, cross-lingual speech generation, emotion control, speaker adaptation, voice conversion, speech editing, and speed editing, making it well suited to narration, dubbing, character voice work, and other expressive speech workflows.

- **Status**: live
- **ID**: `bytedance:seed-audio@1.0`
- Try in Playground
- **Creator**: ByteDance
- **Release Date**: June 4, 2024
- **Capabilities**: Text to Audio, Image to Audio, Audio to Audio, Checkpoint

## Pricing

$0.00263 per second · ~33s per request

**4 example generations**

- [reference-to-audio](https://runware.ai/docs/models/bytedance-seed-audio-1-0/examples#example-wheelchair-rugby-broadcast-victory-stinger): `$0.0266` (~24s)
- [text-to-audio](https://runware.ai/docs/models/bytedance-seed-audio-1-0/examples#example-night-garden-admission-stinger): `$0.0829` (~37s)
- [text-to-audio](https://runware.ai/docs/models/bytedance-seed-audio-1-0/examples#example-substation-maintenance-simulator-ambience): `$0.0848` (~28s)
- [reference-to-audio](https://runware.ai/docs/models/bytedance-seed-audio-1-0/examples#example-flooded-photograph-rescue-narration): `$0.118` (~1m 18s)

times vary, measured end to end · [How pricing works](https://runware.ai/docs/models-api/pricing)

## Compatibility & Validation

Inside `inputs`, `referenceAudios` cannot be used with `referenceImages`.

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/bytedance-seed-audio-1-0#request-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `audioInference`

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/bytedance-seed-audio-1-0#request-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

### [outputType](https://runware.ai/docs/models/bytedance-seed-audio-1-0#request-outputtype)

- **Type**: `string`
- **Default**: `URL`

Audio output type.

**Allowed values**: `URL` `base64Data` `dataURI`

### [outputFormat](https://runware.ai/docs/models/bytedance-seed-audio-1-0#request-outputformat)

- **Type**: `string`
- **Default**: `MP3`

Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities.

- \`MP3\`: Compressed audio, smaller file size.
- \`WAV\`: Uncompressed, high-quality audio.
- \`FLAC\`: Lossless compression.
- \`OGG\`: Open-source compressed audio format (Vorbis codec).

**Allowed values**: `MP3` `WAV` `FLAC` `OGG`

### [audioSettings](https://runware.ai/docs/models/bytedance-seed-audio-1-0#request-audiosettings)

- **Path**: `audioSettings.bitrate`
- **Type**: `object (3 properties)`

Audio encoding settings for controlling the bitrate, number of channels, and sample rate of the generated audio. Only applicable for lossy output formats (`MP3` and `OGG`). When using lossless formats (`WAV` or `FLAC`), this parameter must not be provided.

The available sample rates and valid bitrate ranges depend on the output format. For `OGG`, bitrate limits also vary by the number of channels.

**MP3 bitrate limits**:

Bitrate limits for MP3 are the same regardless of mono or stereo.

| Sample Rate | Min Bitrate | Max Bitrate |
| --- | --- | --- |
| 8,000 Hz | 8 kbps | 64 kbps |
| 11,025 Hz | 8 kbps | 64 kbps |
| 12,000 Hz | 8 kbps | 64 kbps |
| 16,000 Hz | 8 kbps | 160 kbps |
| 22,050 Hz | 8 kbps | 160 kbps |
| 24,000 Hz | 8 kbps | 160 kbps |
| 32,000 Hz | 32 kbps | 320 kbps |
| 44,100 Hz | 32 kbps | 320 kbps |
| 48,000 Hz | 32 kbps | 320 kbps |

**OGG bitrate limits — Mono (1 channel)**:

| Sample Rate | Min Bitrate | Max Bitrate |
| --- | --- | --- |
| 8,000 Hz | 8 kbps | 40 kbps |
| 12,000 Hz | 16 kbps | 48 kbps |
| 16,000 Hz | 16 kbps | 96 kbps |
| 24,000 Hz | 16 kbps | 80 kbps |
| 48,000 Hz | 32 kbps | 224 kbps |

**OGG bitrate limits — Stereo (2 channels)**:

| Sample Rate | Min Bitrate | Max Bitrate |
| --- | --- | --- |
| 8,000 Hz | 16 kbps | 80 kbps |
| 12,000 Hz | 16 kbps | 96 kbps |
| 16,000 Hz | 24 kbps | 192 kbps |
| 24,000 Hz | 32 kbps | 160 kbps |
| 48,000 Hz | 48 kbps | 256 kbps |

> [!NOTE]
> **Lossless formats**: When `outputFormat` is set to `WAV` or `FLAC`, the `audioSettings` parameter is not available since these formats produce uncompressed or lossless audio with no configurable encoding settings.

#### [bitrate](https://runware.ai/docs/models/bytedance-seed-audio-1-0#request-audiosettings-bitrate)

- **Path**: `audioSettings.bitrate`
- **Type**: `integer`
- **Min**: `8`

Audio bitrate in kbps.

#### [channels](https://runware.ai/docs/models/bytedance-seed-audio-1-0#request-audiosettings-channels)

- **Path**: `audioSettings.channels`
- **Type**: `integer`
- **Default**: `2`

Number of audio channels. 1 for mono, 2 for stereo.

**Allowed values**: `1` `2`

#### [sampleRate](https://runware.ai/docs/models/bytedance-seed-audio-1-0#request-audiosettings-samplerate)

- **Path**: `audioSettings.sampleRate`
- **Type**: `integer`

Audio sample rate in Hz.

### [webhookURL](https://runware.ai/docs/models/bytedance-seed-audio-1-0#request-webhookurl)

- **Type**: `string`
- **Format**: `uri`

Webhook URL that receives JSON responses via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.

**Learn more** (1 resource):

- [Webhooks](https://runware.ai/docs/models-api/webhooks) (platform)

### [deliveryMethod](https://runware.ai/docs/models/bytedance-seed-audio-1-0#request-deliverymethod)

- **Type**: `string`
- **Default**: `sync`

Determines how the API delivers task results.

**Allowed values**:

- `sync` Returns results directly in the API response. Over HTTP, a task still running after 120 seconds continues as an async task and comes back with status 'processing'. Poll for its results using getResponse.
- `async` Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

**Learn more** (1 resource):

- [Task Polling](https://runware.ai/docs/models-api/task-polling) (platform)

### [uploadEndpoint](https://runware.ai/docs/models/bytedance-seed-audio-1-0#request-uploadendpoint)

- **Type**: `string`
- **Format**: `uri`

Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials.

**Common use cases:**

- **Cloud storage**: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.
- **CDN integration**: Upload to content delivery networks for immediate distribution.

```text
// S3 presigned URL for secure upload
https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600

// Google Cloud Storage presigned URL
https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789

// Custom storage endpoint
https://storage.example.com/uploads/generated-image.jpg
```

The content data will be sent as the request body to the specified URL when generation is complete.

### [ttl](https://runware.ai/docs/models/bytedance-seed-audio-1-0#request-ttl)

- **Type**: `integer`
- **Min**: `60`

Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`.

### [includeCost](https://runware.ai/docs/models/bytedance-seed-audio-1-0#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/bytedance-seed-audio-1-0#request-numberresults)

- **Type**: `integer`
- **Min**: `1`
- **Max**: `4`
- **Default**: `1`

Number of results to generate. Each result uses a different seed, producing variations of the same parameters.

**Inputs**

Input resources for the task (images, audio, etc). These must be nested inside the \`inputs\` object.

### [referenceImages](https://runware.ai/docs/models/bytedance-seed-audio-1-0#request-inputs-referenceimages)

- **Path**: `inputs.referenceImages`
- **Type**: `array of strings`
- **Min items**: `items: 1`
- **File size (each)**: `up to 10 MB`

List of reference images (UUID, URL, Data URI, or Base64). A single character image whose appearance conditions the generated voice.

### [referenceAudios](https://runware.ai/docs/models/bytedance-seed-audio-1-0#request-inputs-referenceaudios)

- **Path**: `inputs.referenceAudios`
- **Type**: `array of strings`
- **Min items**: `1`
- **Max items**: `3`
- **Duration (each)**: `up to 30s`
- **File size (each)**: `up to 10 MB`

List of reference audios (UUID or URL). Reference clips that condition the generated voice and emotion.

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/bytedance-seed-audio-1-0#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `bytedance:seed-audio@1.0`

Send `auto` instead of an AIR identifier to have the model router choose the model for this task. The rest of the request is unchanged, every value you send is kept, and only the parameters you leave out are filled in. See [Model Router](https://runware.ai/docs/models-api/model-router).

**Learn more** (3 resources):

- [Text To Image: Model Selection](https://runware.ai/docs/learn/text-to-image#model-selection) (learn)
- [Image Inpainting: Model Specialized Inpainting Models](https://runware.ai/docs/learn/image-inpainting#model-specialized-inpainting-models) (learn)
- [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/learn/image-outpainting#other-critical-parameters) (learn)

### [positivePrompt](https://runware.ai/docs/models/bytedance-seed-audio-1-0#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **Max**: `2048`

Text prompt describing the voice, environment, background music, sound effects, and dialogue to synthesize. In audio-reference mode, reference clips in array order as `@Audio1`, `@Audio2`, and `@Audio3`.

**Learn more** (1 resource):

- [Prompts](https://runware.ai/docs/learn/prompts) (learn)

### [speech](https://runware.ai/docs/models/bytedance-seed-audio-1-0#request-speech)

- **Path**: `speech.volume`
- **Type**: `object (3 properties)`

Settings for speech generation.

#### [volume](https://runware.ai/docs/models/bytedance-seed-audio-1-0#request-speech-volume)

- **Path**: `speech.volume`
- **Type**: `integer`
- **Min**: `-50`
- **Max**: `100`
- **Step**: `1`
- **Default**: `0`

Volume level of the generated speech. `100` produces 2.0x volume, `0` leaves volume unchanged, and `-50` produces 0.5x volume.

#### [speed](https://runware.ai/docs/models/bytedance-seed-audio-1-0#request-speech-speed)

- **Path**: `speech.speed`
- **Type**: `integer`
- **Min**: `-50`
- **Max**: `100`
- **Step**: `1`
- **Default**: `0`

Playback speed of the generated speech. `100` produces 2.0x speed, `0` is the normal rate, and `-50` produces 0.5x speed.

#### [pitch](https://runware.ai/docs/models/bytedance-seed-audio-1-0#request-speech-pitch)

- **Path**: `speech.pitch`
- **Type**: `integer`
- **Min**: `-12`
- **Max**: `12`
- **Step**: `1`
- **Default**: `0`

Pitch adjustment for the voice.

## Response Parameters

### [taskType](https://runware.ai/docs/models/bytedance-seed-audio-1-0#response-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `audioInference`

Identifier for the type of task this response belongs to.

### [taskUUID](https://runware.ai/docs/models/bytedance-seed-audio-1-0#response-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier echoed from the original request, used to match async responses to their tasks.

### [audioUUID](https://runware.ai/docs/models/bytedance-seed-audio-1-0#response-audiouuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID of the output audio.

### [audioURL](https://runware.ai/docs/models/bytedance-seed-audio-1-0#response-audiourl)

- **Type**: `string`
- **Format**: `uri`

URL of the output audio.

### [audioBase64Data](https://runware.ai/docs/models/bytedance-seed-audio-1-0#response-audiobase64data)

- **Type**: `string`

Base64-encoded audio data.

### [audioDataURI](https://runware.ai/docs/models/bytedance-seed-audio-1-0#response-audiodatauri)

- **Type**: `string`
- **Format**: `uri`

Data URI of the output audio.

### [cost](https://runware.ai/docs/models/bytedance-seed-audio-1-0#response-cost)

- **Type**: `float`

Task cost in USD. Present when `includeCost` is set to `true` in the request.

## Examples

### text-to-audio (text-to-audio)

[Listen to audio](https://assets.runware.ai/examples/bytedance-seed-audio-1-0/9ed82113-d110-477b-bfda-66789b96ee05.mp3)

```json
{
  "taskType": "audioInference",
  "taskUUID": "10e98c6e-9aa2-4903-a73a-e02985249c6d",
  "model": "bytedance:seed-audio@1.0",
  "positivePrompt": "Create an elegant admission stinger for a botanical conservatory’s nighttime tour. Begin with three luminous glass-marimba notes forming a memorable audio logo, joined by soft bass clarinet, brushed frame drum, and a warm sustained string harmonic. Add a subtle outdoor night ambience with crickets, distant tree frogs, leaves moving in a light breeze, and one delicate iron gate latch. A poised adult female guide speaks with intimate warmth, quiet wonder, and precise diction: “Welcome to the Moonflower Walk. Keep to the lantern path, let the night bloom around you, and leave every petal where it grows.” Keep the voice centered and fully intelligible. Let the final word resolve into the returning three-note glass-marimba motif, followed by a faint shimmer and natural garden ambience. Refined, mysterious, welcoming, and suitable for playback at the entrance to a premium cultural attraction; no ominous tones, no crowd noise, and no exaggerated fantasy effects."
}
```

---

### text-to-audio (text-to-audio)

[Listen to audio](https://assets.runware.ai/examples/bytedance-seed-audio-1-0/c749f7b6-a030-47ea-9d32-bd2b5eb97a59.mp3)

```json
{
  "taskType": "audioInference",
  "taskUUID": "76d8f9ea-a3a0-45ae-abab-6c8c439b76f7",
  "model": "bytedance:seed-audio@1.0",
  "positivePrompt": "Create a hyperrealistic ambient sound bed for an electrical utility maintenance simulator at a large outdoor high-voltage substation just before dawn. Establish a steady low transformer hum, layered 60 Hz electrical resonance, cooling fans, occasional relay clicks, faint insulator buzz, light wind across chain-link fencing, boots shifting on gravel, and distant road traffic. Add one brief handheld-radio transmission from a calm, experienced female grid controller. Her delivery is precise, reassuring, and safety-focused, with narrow-band radio coloration and a short squelch burst before and after. Spoken verbatim: “Control to field team. Breaker seven is isolated and tagged. Confirm the ground is visible before entering the work zone.” Keep the announcement fully intelligible above the machinery. Afterward, return naturally to the stable environmental bed. No alarm, electrical arc, dramatic impact, melody, or background music; the mood is vigilant, procedural, and controlled."
}
```

---

### reference-to-audio (reference-to-audio)

[Listen to audio](https://assets.runware.ai/examples/bytedance-seed-audio-1-0/be91682f-aa69-41ab-a2a6-ca91462df165.mp3)

```json
{
  "taskType": "audioInference",
  "taskUUID": "4b1e936e-6a7a-4b9b-8f88-6c575db63317",
  "model": "bytedance:seed-audio@1.0",
  "positivePrompt": "Create a finished wheelchair rugby broadcast victory stinger with an athlete-first, high-impact sports identity. Use @Audio1 to establish the female alto voice identity and its fierce, controlled confidence; transform the spoken line into a tight, pitched three-note chant while preserving the vocalist's recognizable timbre: “POINT SECURED — OWN THE COURT!” Open with two crisp wheelchair-rim clacks, then hit a muscular breakbeat, low taiko, distorted baritone synth pulse, and a sharp brass accent. Add a brief authentic indoor-arena crowd surge behind the hook. End on one decisive metallic impact with a clean sub-bass tail. Modern brutalist sound design, exhilarating rather than sentimental, broadcast-loud and punchy, intelligible vocal, strong transient detail, no announcer, no extra words, no fade-in.",
  "inputs": {
    "referenceAudios": [
      "https://assets.runware.ai/assets/inputs/06e758e0-0f53-481a-842f-f9dfab7900e7.mp3"
    ]
  }
}
```

---

### reference-to-audio (reference-to-audio)

[Listen to audio](https://assets.runware.ai/examples/bytedance-seed-audio-1-0/5ccb3143-2c8a-467a-8989-2eda72f6e193.mp3)

```json
{
  "taskType": "audioInference",
  "taskUUID": "02542f4b-e722-4c46-aa65-022efd73eec1",
  "model": "bytedance:seed-audio@1.0",
  "positivePrompt": "Produce a clean, studio-quality e-learning narration for museum collection staff. Use @Audio1 to condition the narrator's identity, measured authority, calm warmth, and precise instructional cadence. The delivery should feel reassuring during an emergency without sounding casual or dramatic. Moderate pace, crisp consonants, brief pauses between procedural steps, and gentle emphasis on “do not separate them.” No music, sound effects, room ambience, or introductory announcement. Speak only this script verbatim:\n\n“When photographs are soaked, their softened image layers can stick to neighboring surfaces. First, support each item from beneath with a rigid tray. Never lift it by a corner. If several photographs are adhered together, do not separate them. Keep the stack wet, place it flat in a clean polyethylene bag, and label the bag with its original location. Move loose photographs image-side up onto absorbent paper, leaving space between them. Change the paper as it becomes damp, but avoid touching the image surface. These steps stabilize the collection; a photograph conservator should make all final treatment decisions.”",
  "inputs": {
    "referenceAudios": [
      "https://assets.runware.ai/assets/inputs/db83abcd-2609-4a79-a2f3-bfd814398ddf.mp3"
    ]
  }
}
```