ByteDance Seed Audio 1.0 Text to Audio API

ByteDance Seed Audio

ByteDance Seed Audio generates natural speech and audio from a text prompt. It supports preset voices, optional reference audio clips, optional image guidance, and common audio output controls such as format, sample rate, speed, volume, and pitch.

Why Choose This?

Natural speech and audio generation
Generate speech or audio directly from a text prompt.
Preset voice support
Choose from multiple preset voices for text-to-speech generation.
Reference audio guidance
Upload up to 3 reference audio clips to guide the generated voice or audio style.
Image guidance support
Provide a single reference image to guide audio generation.
Flexible audio controls
Adjust output format, sample rate, speed, volume, and pitch to match your workflow.

Parameters

Parameter	Required	Description
prompt	Yes	Text or audio prompt to synthesize.
audios	No	Optional reference audio URLs. Upload up to 3 clips. Do not use together with `image`.
image	No	Optional single reference image URL. Do not use together with `audio`.
output_format	No	Audio output format: `wav`, `mp3`, `pcm`, or `ogg_opus`. Default: `mp3`.
sample_rate	No	Output sample rate in Hz. Supported values: `8000`, `16000`, `24000`, `32000`, `44100`, `48000`. Default: `24000`.
speed	No	Speech speed multiplier. Range: `0.5` to `2`. Default: `1`.
volume	No	Speech volume multiplier. Range: `0.5` to `2`. Default: `1`.
pitch	No	Pitch shift in semitones. Range: `-12` to `12`. Default: `0`.

How to Use

Write your prompt — Enter the text or audio description you want to synthesize.
Add reference audio optional — Upload up to 3 audio clips when you want reference-based voice or audio guidance.
Add image guidance optional — Use image when you want to guide generation from a single reference image.
Set audio controls optional — Choose output format, sample rate, speed, volume, and pitch.
Submit — Generate the final audio output.

Pricing

Just $0.3 per generate.

Best Use Cases

Text-to-speech generation — Convert written text into natural spoken audio.
Voice-guided speech generation — Use reference audio clips to guide the generated voice or audio style.
Image-guided audio generation — Use a reference image to guide audio creation.
Narration and dialogue — Generate voice audio for videos, demos, apps, and creative projects.
Audio prototyping — Test different voices, speeds, volumes, pitches, and output formats.

Pro Tips

Use a clear and focused prompt for more stable audio generation.
Use clean reference audio clips when voice or style guidance matters.
Use mp3 for general-purpose output and smaller file size.
Use wav when you need higher-quality audio for post-production.
Adjust speed, volume, and pitch only when you need specific delivery control.
Ensure reference audio and image URLs are publicly accessible.

Seed Audio 1.0 API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/bytedance/seed-audio-1.0 with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read URLs from data.outputs. Examples for Seed Audio 1.0 below.

HTTP example

# Submit the prediction
curl --fail-with-body --connect-timeout 10 --max-time 60 \
  -X POST "https://api.wavespeed.ai/api/v3/bytedance/seed-audio-1.0" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d '{
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "output_format": "mp3",
    "sample_rate": 24000,
    "speed": 1,
    "volume": 1,
    "pitch": 0
}'

# Wait at least 2 seconds, then poll. Safe GET requests may be retried.
curl --fail-with-body --connect-timeout 10 --max-time 30 \
  --retry 4 --retry-all-errors --retry-delay 1 \
  -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY"

# Start at 2 seconds and increase the interval for long-running tasks.
# Stop on completed, failed, cancelled, or timeout.

Node.js example

// npm install wavespeed
const { Client } = require('wavespeed');

const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');
const client = new Client(apiKey);

try {
  const result = await client.run("bytedance/seed-audio-1.0", {
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "output_format": "mp3",
        "sample_rate": 24000,
        "speed": 1,
        "volume": 1,
        "pitch": 0
}, {
    timeout: 3600,
    pollInterval: 2.0,
  });
  console.log(result.outputs);
} catch (error) {
  console.error('Generation failed:', error);
  process.exitCode = 1;
}

Python example

# pip install wavespeed
import os
from wavespeed import Client

client = Client(api_key=os.environ["WAVESPEED_API_KEY"])

try:
    output = client.run(
        "bytedance/seed-audio-1.0",
        {
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "output_format": "mp3",
    "sample_rate": 24000,
    "speed": 1,
    "volume": 1,
    "pitch": 0
},
        timeout=3600.0,
        poll_interval=2.0,
    )
    print(output["outputs"])
except Exception as error:
    raise SystemExit(f"Generation failed: {error}") from error

Seed Audio 1.0 API — Frequently asked questions

What is the Seed Audio 1.0 API?

Seed Audio 1.0 is a ByteDance model for audio generation, exposed as a REST API on WaveSpeedAI. ByteDance Seed Audio 1.0 Text to Audio generates natural speech and audio from text prompts, with optional preset voice, reference audio, or reference image guidance for flexible audio creation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Seed Audio 1.0 API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/bytedance/bytedance-seed-audio-1.0.

How much does Seed Audio 1.0 cost per run?

Seed Audio 1.0 starts at $0.30 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Seed Audio 1.0 accept?

Key inputs: `prompt`, `image`, `audios`, `output_format`, `pitch`, `sample_rate`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/bytedance/bytedance-seed-audio-1.0.

How do I get started with the Seed Audio 1.0 API?

Sign up for a free WaveSpeedAI account to claim starter credits, copy your API key from /accesskey, then call the endpoint shown in the API tab of the playground. The playground also auto-generates a code sample in Python, JavaScript, or cURL for the parameters you've set.

Can I use Seed Audio 1.0 outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (ByteDance). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.

サンプルすべて表示

関連モデル

README