Audio Generation

Seed Audio 1.0 API

ByteDance Seed Audio 1.0. Generate speech, voice clones, and full audio scenes (radio dramas, podcasts, narration) from a prompt. Integrate this model via REST with endpoint docs, parameters, and code examples.

Prompting guide

Credit Cost

0.1 credits/sec

Type

Audio

Get API Key

Create auth keys for apps and agents

See Usage

Track requests, credits, and logs

Buy Credits

Top up prepaid API capacity

API Endpoint

POST

/api/v1/models/seed-audio/run

Test This Model

Run a real request through the API pipeline and inspect the exact input and output your integration will handle. Uses your credits like any API call; failed runs are refunded automatically.

LLM.txt

AI-Ready

For AI assistants

Copy this model's documentation into Claude, GPT, or any AI for instant integration help.

/llm/seed-audio.txt

OpenAPI Spec

Swagger compatible

Import into Postman, Swagger UI, or generate client SDKs in any language.

/api/openapi

Parameters

Input parameters accepted by this model

Parameter	Type	Description	Default
`prompt` required	string	Text to speak, or an instruction like "Generate a short suspense radio drama". Reference uploaded audio clips inline as @Audio1, @Audio2, @Audio3.	-
`voice`	string	Accepted for backwards compatibility but no longer applied. The model has no preset-voice control. Describe the voice you want in the prompt, or clone one with audio_urls.	-
`audio_urls`	array	Up to 3 reference audio URLs for voice cloning, referenced in the prompt as @Audio1–@Audio3. Each clip up to 30s / 10MB (wav, mp3, pcm, or ogg_opus). Cannot be combined with image_url. items: url max items: 3	-
`image_url`	url	Single reference image URL (jpeg/png/webp, up to 10MB) to guide the audio. Cannot be combined with audio_urls.	-
`output_format`	enum	Output audio format. `mp3wavpcmogg_opus`	`mp3`
`sample_rate`	integer	Output sample rate in Hz (8000, 16000, 24000, 32000, 44100, or 48000).	`24000`
`speed`	number	Speech speed multiplier (0.5–2). min: 0.5 \| max: 2	`1`
`volume`	number	Volume multiplier (0.5–2). min: 0.5 \| max: 2	`1`
`pitch`	integer	Pitch shift in semitones (-12 to +12). min: -12 \| max: 12	`0`

Use saved characters (@Name)

This model takes no reference images, so @Name of a saved character is refused (400) before anything is charged. A saved location, prop or style with a description is inserted as text. For saved characters, use a model that takes reference images, such as Nano Banana Pro or Seedream 5 for images, or Seedance 2.5 or WAN 3.0 for video.

Code Examples

Narration with a described voice: copy and paste to get started

bash

curl -X POST "https://pixeldojo.ai/api/v1/models/seed-audio/run" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A warm male narrator, unhurried: Welcome to PixelDojo, where ideas become images."
  }'

Response Format

Submit Response (202 Accepted)

json

{
  "jobId": "job_abc123...",
  "status": "pending",
  "statusUrl": "https://pixeldojo.ai/api/v1/jobs/job_abc123...",
  "creditCost": 1,
  "creditsRemaining": 95,
  "expiresAt": "2026-10-30T11:01:49Z"
}

Completed Response

json

{
  "jobId": "job_abc123...",
  "status": "completed",
  "output": {
    "audio": "https://temp.pixeldojo.ai/pixeldojotemp/1705930123-456789.mp3"
  },
  "creditCost": 1,
  "expiresAt": "2026-10-30T11:01:49Z"
}

LLM Documentation Try in Web UI Get API Key Usage Dashboard Buy Credits