Skip to content
Model infoModelsSnapshot: 15 Oct 2026

ByteDance / Seed Audio

Seed Audio 1.0

Audio scene generation combining speech, effects and ambience, with text, audio or image references.

Sound effectsSpeech & voice
availableClosed weightsText-to-speechSound effects generation
Official documentation (opens in a new tab)Reviewed 12 Oct 2026
13 of 23 specification fields collected
Text input limit3,000 charactersSee specification notes below
Languages20 listedFull language list in specifications
Input billingSee ratesBytePlus Seed Speech
Output billingSee ratesPublished units and conditions below

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
Not collected
Maximum output
Not collected
Input modalities
Text, Audio, ImageSource for Input modalities (opens in a new tab)
Output modalities
AudioSource for Output modalities (opens in a new tab)
Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected
Streaming
Not supportedSource for Streaming (opens in a new tab)

The direct BytePlus API is explicitly non-streaming.

Batch processing
Not collected
Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
2026-07-20Source for Release date (opens in a new tab)
Parameters
Not collected
Architecture
A unified acoustic representation for speech and other scene soundsSource for Architecture (opens in a new tab)
Languages
View all 20 entries
  • English
  • Chinese
  • Japanese
  • Korean
  • Mexican Spanish
  • Indonesian
  • German
  • Brazilian Portuguese
  • French
  • Thai
  • Vietnamese
  • Malay
  • Filipino
  • Italian
  • Russian
  • Dutch
  • Polish
  • Turkish
  • Swedish
  • Castilian Spanish
Source for Languages (opens in a new tab)

The source splits Brazilian and Portuguese into adjacent code spans; represented as Brazilian Portuguese.

Context caching
Not collected
Maximum prompt characters
3,000 charactersSource for Maximum prompt characters (opens in a new tab)
Audio duration limits
Up to 120 seconds of generated audio per requestSource for Audio duration limits (opens in a new tab)
Audio formats
WAV, MP3, PCM, OGG_OPUSSource for Audio formats (opens in a new tab)
Audio sample rates
8,000; 16,000; 24,000; 32,000; 44,100; 48,000 HzSource for Audio sample rates (opens in a new tab)
Voice references
At most 3 clips, each at most 30 seconds and 10 MB; WAV, MP3, PCM or OGG_OPUSSource for Voice references (opens in a new tab)
Reference images
One JPEG, PNG or WebP image, at most 10 MB; cannot be mixed with audio referencesSource for Reference images (opens in a new tab)
Word timestamps
SupportedSource for Word timestamps (opens in a new tab)

Optional enable_subtitle output.

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

BytePlus Seed Speech · Non-streaming HTTP

Provider source (opens in a new tab)
API model ID
seed-audio-1.0

Provider model selector or X-Api-Resource-Id as documented; it is not a user voice ID.

Access
Enable Seed Speech for an eligible BytePlus account and use the documented resource selector. Voice permissions and concurrency limits apply.
Regions
ap-southeast-1 API endpoint; other regions not verified
Service tier
Non-streaming HTTPSource for Service tier (opens in a new tab)
Streaming
Not supportedSource for Streaming (opens in a new tab)
API endpoint URL
https://voice.ap-southeast-1.bytepluses.com/api/v3/tts/createSource for API endpoint URL (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Audio generationOutput1$0.0025second

Rate conditions

  1. Generated-audio duration, billed with second precision; equivalent to $0.15/minute. No prepaid package or free-trial discount assumed.
Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

fal · Hosted audio generation

Provider source (opens in a new tab)
API model ID
bytedance/seed-audio-1.0

Provider model selector or X-Api-Resource-Id as documented; it is not a user voice ID.

Access
Hosted fal API; requires an eligible account and API key.
Regions
Not collected
Service tier
Hosted audio generationSource for Service tier (opens in a new tab)
Audio formats
WAV, MP3, PCM, OGG_OPUSSource for Audio formats (opens in a new tab)
Default audio format
MP3Source for Default audio format (opens in a new tab)
Default audio sample rate
24,000 HzSource for Default audio sample rate (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Audio generationOutput1$0.1875minute

Rate conditions

  1. fal’s published hosted rate. This is not the direct BytePlus rate.
Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

BytePlus Seed Speech · Non-streaming HTTP

seed-audio-1.0
Not verified
How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
Not collected

No verified cache rate for this endpoint. An empty rate is not a zero charge.

fal · Hosted audio generation

bytedance/seed-audio-1.0
Not verified
How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
Not collected

No verified cache rate for this endpoint. An empty rate is not a zero charge.

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Inferred from the native hosted model/resource identifier and the reviewed ByteDance/ByteDance-Seed public-checkpoint inventories. These inventories contain no matching released checkpoint; this is not an explicit weight-license declaration.

Classification evidence (opens in a new tab)

Sources reviewed