Seed Audio 1.0 API

About Seed Audio 1.0

ByteDance Seed's all-in-one audio model: describe the speakers, their lines in quotes, plus any music, ambience and sound effects in a single prompt, and get back one MP3 of up to about two minutes.

Call it with the model name bytedance/seed-audio-1.0/text-to-audio on POST /jobs/createTask, from 54 credits per run ($0.54). New accounts get 30 free credits to try it in the Playground first.

Introduction

Seed Audio 1.0 turns one written description into one audio file of up to about two minutes: speech, music, ambience and sound effects together, as an MP3 unless you set output_format. There is no voice list. Describe who speaks and how, quote their exact words, and add the sounds around them in the same prompt (up to 2,000 characters). To reuse a voice or a sound, attach reference clips; to voice a picture, attach an image.

Key features

A whole scene from one prompt

Speakers, their lines, music, ambience and effects all come from one description, so the clip arrives already mixed.

More than one speaker

Describe each character and their lines, and the model gives each a distinct voice in the same clip.

Reference audio

Upload up to three clips in reference_audio_urls and name them in the prompt as @Audio1, @Audio2 and @Audio3, in upload order, for example "Using the voice of @Audio1, a man says …".

Voice a picture

Give one picture in image_url and describe what the person in it says or how the scene sounds. Reference audio and an image cannot be combined in one request.

Request parameters

Pricing

Prices are in credits, the same credits you use on the website (1 credit = $0.01). The hold is taken when the task is accepted and settled to the actual charge when it finishes; failed tasks are refunded.

For an exact number before you run, send the same body to POST /jobs/quote.

Use cases

Short audio dramas and ads

A two-character exchange with a café in the background, or a product line read over light music, comes back as one finished clip.

Sound for a still or a storyboard frame

Attach the frame as image_url and describe what is heard: the speaker's line, the room, the weather.

A consistent voice across clips

Keep one approved clip as @Audio1 and reuse it in every request for a series.

Prompt guide & pro tips

Write it like a script

Who is speaking and how (a whisper, a warm narrator, a shouted line), then their exact words in quotes, then the music, ambience and effects you want alongside.

Use references you have the right to use

Only upload voices, sounds and images you are allowed to use.

Fine-tune instead of rewriting

speed (0.5–2), pitch (-12 to 12 semitones) and volume (0.5–2) adjust the delivery without changing the prompt.

Pick a playable format

output_format takes mp3 (default), wav, opus (Ogg Opus) or pcm, and sample_rate goes from 8000 to 48000 Hz. pcm is raw samples with no header and cannot be previewed in a browser; choose wav for the same samples in a playable file.

API quick start

Call the Seed Audio 1.0 API in three steps

1. Create an API key. Sign in to PopNow and create a key in the API console. Keys start with sk-popnow- and use the same credits as the website.
2. Send the request. POST /jobs/createTask with model bytedance/seed-audio-1.0/text-to-audio and an input object that follows the parameter table. The response returns a task ID straight away.
3. Get the result. Poll GET /jobs/recordInfo with the task ID, or pass a callBackUrl and we post the result to it. Download the output links when the task succeeds.

# 1. Create the task. Keep the Idempotency-Key if you retry after a network error.
export IDEMPOTENCY_KEY="$(uuidgen)"
curl -X POST https://api.popnow.ai/api/v1/jobs/createTask \
  -H "Authorization: Bearer $POPNOW_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $IDEMPOTENCY_KEY" \
  -d '{
  "model": "bytedance/seed-audio-1.0/text-to-audio",
  "input": {
    "prompt": "Calm ambient pads with a slow rising motif",
    "output_format": "mp3"
  }
}'

# 2. Copy data.taskId from the response, then poll until state is succeeded, failed, canceled or expired.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
  -H "Authorization: Bearer $POPNOW_API_KEY"

Replace the prompt and any links with your own. The API tab has the response, polling and callback reference.

Seed Audio 1.0 API questions

More about Seed Audio 1.0

Try it

Seed Audio 1.0 AI Sound Effects Generator onlineCreate audio with Seed Audio 1.0 in PopNow

Docs

Seed Audio 1.0 model ID and input schema in the API docsPopNow API quickstart: your first request in five minutesWebhooks: get Seed Audio 1.0 results without polling