ByteDance · Text to Audio

Seed Audio 1.0

All-in-one audio generation: dialogue, music, ambience, and sound effects in one pass, with zero-shot voice cloning from up to 3 reference clips (under 30s each).

text → audio

bytedance/seed-audio-1.0/text-to-audio

Capabilities

Best for

•Voiceover and narration
•Sound design beds
•Quick music sketches

Not for

•Real-time streaming synthesis
•Studio mastering
•Forensic audio

Authentication

api key header

The Pika API uses API keys to authenticate requests. Send your key in the X-API-Keyheader. Your API key is a secret. Don't expose it in browsers or other client-side code. Instead, call the API from your server. The signed-in playground uses a portal session and never sends your API key.

header

X-API-Key: YOUR_API_KEY

Endpoint

asynchronous · poll for the result

POSThttps://089e99349ace.pikalabs.app/v1/media/bytedance/seed-audio-1.0/text-to-audiogenerate endpoint

GEThttps://089e99349ace.pikalabs.app/v1/media/jobs/{request_id}poll until completed

GEThttps://089e99349ace.pikalabs.app/v1/media/jobs/{request_id}/contentget the result URL

Reference Uploads

media inputs

Media inputs accept any public URL. To use a local file, POST its content_type and size_bytes to /v1/media/uploads, PUT the file to the returned upload_url, then pass the url.

upload

# 1. Request a presigned upload URL. Send the file's content
#    type and its exact size in bytes.
curl -X POST https://089e99349ace.pikalabs.app/v1/media/uploads \
  -H "X-API-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"content_type": "image/png", "size_bytes": 12345}'

# The response returns two URLs:
#   upload_url: a temporary URL to upload the file to. Expires in 5 minutes.
#   url:        the permanent Pika URL. Pass it to the model as the input.
# {
#   "upload_url": "https://upload.r2.pika.art/...?X-Amz-Signature=...",
#   "url": "https://cdn.pika.art/v2/media/uploads/org_abc/9f8e7d.png"
# }

# 2. Upload the file to upload_url, then pass url to the model.
curl -X PUT "<upload_url>" \
  -H "Content-Type: image/png" \
  --data-binary @input.png

Generate

POST /v1/media/bytedance/seed-audio-1.0/text-to-audio

Request

curl -X POST https://089e99349ace.pikalabs.app/v1/media/bytedance/seed-audio-1.0/text-to-audio \
  -H "X-API-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "prompt": "Slow push-in as the huge eyes blink and subtly track the camera; the surrounding flowers nod in a light breeze and clouds drift across the blue sky. Surreal, uncanny calm.",
  "output_format": "mp3"
}'

Response

{
  "id": "media_8f3a2c91-5b7d-4e0a-9c26-31d4f2a8e6b0",
  "status": "queued"
}

Request body

promptstringrequired

What to generate — dialogue, music, ambience, and sound effects in one pass. Reference supplied clips as @Audio1…@Audio3. Output up to ~120 seconds.

voicestring

Preset speaker id. Counts toward the 3 voice/audio reference cap.

audio_urlsstring[]

Up to 3 voice-cloning reference clips, EACH UNDER 30 SECONDS; refer to them in the prompt as @Audio1…@Audio3. Cannot be combined with image_url.

image_urlstring

A single image reference (the generated voice/scene matches it). Cannot be combined with voice or audio_urls.

output_formatenumdefault: mp3

Output Format

sample_rateenum

Sample Rate

speednumber0.5 – 2

Speed

volumenumber0.5 – 2

Volume

pitchinteger-12 – 12

Pitch

Accepted values

output_format
sample_rate

Input modes

Audio urlsaudio_urls

Use a public URL directly, or POST { content_type, size_bytes } to /v1/media/uploads, PUT the audio to the returned upload_url, then pass the url.

Image urlimage_url

Use a public URL directly, or POST { content_type, size_bytes } to /v1/media/uploads, PUT the image to the returned upload_url, then pass the url.

Returns

Returns a job object with status , not the final output. Store the id from the response and poll the job until it completes.

Poll status

GET /v1/media/jobs/{request_id}

Request

curl https://089e99349ace.pikalabs.app/v1/media/jobs/{request_id} \
  -H "X-API-Key: YOUR_API_KEY"

Response

{
  "id": "media_8f3a2c91-5b7d-4e0a-9c26-31d4f2a8e6b0",
  "status": "running"
}

Poll the job by id until it reaches a terminal state: completed or failed.

The job object

idstring

Unique identifier for the job.

statusenum

The status of the job.One of:

object

The generation output. Present once the job completes.

errorstring

If the job failed, the reason for the failure.

Get result

GET /v1/media/jobs/{request_id}/content

Request

curl https://089e99349ace.pikalabs.app/v1/media/jobs/{request_id}/content \
  -H "X-API-Key: YOUR_API_KEY"

Response

{
  "url": "https://089e99349ace.pikalabs.app/v1/files/audio_8f3a2c91.mp3"
}

Once the job completes, fetch a download URL for the generated media.

Returns

urlstring

Download URL for the generated file.

Errors

shared across calls

Errors use conventional HTTP status codes with a JSON body of the shape {"message": "..."}. The one exception is validation: a request body that fails validation returns 422 with a plain-text body.

Status	When	Body
401 Unauthorized	The API key is missing or invalid.	{"message":"Invalid API key"}
403 Forbidden	The key is not active, or the org balance cannot cover the request.	{"message":"Insufficient org balance"}
404 Not Found	No job with that id exists in your org.	{"message":"media job not found"}
409 Conflict	The result was requested before the job completed, or an Idempotency-Key header was reused with a different body.	{"message":"media job is not ready"}
422 Unprocessable Entity	The request body failed validation: an invalid enum value, a missing required field, a wrong type, or malformed JSON. Returned as plain text, not JSON. A schema-valid parameter combination that cannot be priced returns the same status with a JSON message.	Unprocessable entity
429 Too Many Requests	Org limit reached: requests per minute or day, or concurrent jobs. Check the Retry-After header.	{"message":"rate limit exceeded: rpm"}
503 Service Unavailable	The model rail or a backend dependency is temporarily unavailable. Retry with backoff.	{"message":"media dispatch unavailable"}

Pricing

only successful runs are charged

Tier	Price
default	$0.003 / second

Per-model pricing

Transparent, usage-based rates for every ByteDance model.

Model	Type
Seed Audio 1.0Current	Text to Audio	$0.003 / sec
Seedream 4.0	Text to Image	$0.032 / image
Seedream 5.0 Lite	Text to Image	$0.037 / image
Seedream 4.5	Text to Image	$0.042 / image
Seedance 2.0 Mini	Reference to Video	from $2.205
Seedance 2.0	Reference to Video	from $2.52
Seedance 2.0 Fast	Reference to Video	from $3.465
Seedance 2.0 Mini	Image to Video	$3.675
Seedance 2.0 Mini	Text to Video	$3.675
Seedance 2.0	Image to Video	from $4.2
Seedance 2.0	Text to Video	from $4.2
Seedance 2.0 Fast	Image to Video	$5.88
Seedance 2.0 Fast	Text to Video	$5.88

Seed Audio 1.0

Current

$0.003 / sec

Text to Audio

Seedream 4.0

$0.032 / image

Text to Image

Seedream 5.0 Lite

$0.037 / image

Text to Image

Seedream 4.5

$0.042 / image

Text to Image

Seedance 2.0 Mini

from $2.205

Reference to Video

Seedance 2.0

from $2.52

Reference to Video

Seedance 2.0 Fast

from $3.465

Reference to Video

Seedance 2.0 Mini

$3.675

Image to Video

Seedance 2.0 Mini

$3.675

Text to Video

Seedance 2.0

from $4.2

Image to Video

Seedance 2.0

from $4.2

Text to Video

Seedance 2.0 Fast

$5.88

Image to Video

Seedance 2.0 Fast

$5.88

Text to Video