Skip to content
Model infoModelsSnapshot: 15 Oct 2026

ByteDance / Seed ASR

Seed ASR 2.0

Speech recognition with multilingual transcription, timestamps and endpoint-specific speaker analysis.

Transcription
availableClosed weightsTranscription
Official documentation (opens in a new tab)Reviewed 12 Oct 2026
9 of 21 specification fields collected
Audio durationStandard file: up to 5 hours; other modes have separate limitsSee specification notes below
File size limitStandard file: less than 512 MBSee specification notes below
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
Audio, Text, ImageSource for Input modalities (opens in a new tab)

Audio is the recognition input. Optional text/image context assists recognition on the documented current API.

Output modalities
TextSource for Output modalities (opens in a new tab)
Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected
Streaming
SupportedSource for Streaming (opens in a new tab)
Batch processing
Not collected
Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
Not collected
Parameters
Not collected
Architecture
Not collected
Languages
View all 51 entries
  • English
  • Mandarin Chinese
  • Cantonese
  • Japanese
  • Indonesian Bahasa
  • Spanish
  • Portuguese
  • German
  • French
  • Korean
  • Filipino
  • Malay
  • Thai
  • Arabic
  • Italian
  • Bengali
  • Greek
  • Dutch
  • Russian
  • Turkish
  • Vietnamese
  • Polish
  • Romanian
  • Nepali
  • Ukrainian
  • Azerbaijani
  • Bulgarian
  • Czech
  • Danish
  • Finnish
  • Hausa
  • Hindi
  • Hungarian
  • Hebrew
  • Kazakh
  • Khmer
  • Kannada
  • Kurdish
  • Malayalam
  • Marathi
  • Burmese
  • Norwegian
  • Punjabi
  • Pashto
  • Sindhi
  • Swedish
  • Swahili
  • Tamil
  • Telugu
  • Urdu
  • Zulu
Source for Languages (opens in a new tab)

51-language coverage is stated for audio-file and unidirectional streaming modes, not every bidirectional configuration.

Context caching
Not collected
Audio duration limits
Standard file: up to 5 hours; other modes have separate limitsSource for Audio duration limits (opens in a new tab)
Maximum audio file
Standard file: less than 512 MBSource for Maximum audio file (opens in a new tab)
Word timestamps
SupportedSource for Word timestamps (opens in a new tab)
Custom vocabulary
SupportedSource for Custom vocabulary (opens in a new tab)
Speaker diarization
SupportedSource for Speaker diarization (opens in a new tab)

Audio-file mode, Chinese/English. The overview marks streaming diarization unsupported.

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 · Bidirectional streaming

Provider source (opens in a new tab)
API model ID
volc.seedasr.sauc.duration

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
Bidirectional streamingSource for Service tier (opens in a new tab)
API aliases
request.model_name=bigmodelSource for API aliases (opens in a new tab)

The model resource header chooses the revision; bigmodel alone does not identify it.

Streaming
SupportedSource for Streaming (opens in a new tab)
Speaker diarization
Not supportedSource for Speaker diarization (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
TranscriptionInput audio1$0.15hour

Rate conditions

  1. Published ASR service-level PAYG rate for this processing mode. Optional concurrency and prepaid packages are separate; not a language-model token 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.

BytePlus Seed Speech · Asynchronous audio file

Provider source (opens in a new tab)
API model ID
volc.seedasr.auc

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
Asynchronous audio fileSource for Service tier (opens in a new tab)
API aliases
request.model_name=bigmodelSource for API aliases (opens in a new tab)

The model resource header chooses the revision; bigmodel alone does not identify it.

Streaming
Not supportedSource for Streaming (opens in a new tab)
Audio duration limits
Up to 5 hoursSource for Audio duration limits (opens in a new tab)
Maximum audio file
Less than 512 MBSource for Maximum audio file (opens in a new tab)
Speaker diarization
SupportedSource for Speaker diarization (opens in a new tab)

Chinese and English; speaker separation works best with at most 10 speakers.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
TranscriptionInput audio1$0.12hour

Rate conditions

  1. Published ASR service-level PAYG rate for this processing mode. Optional concurrency and prepaid packages are separate; not a language-model token 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.

BytePlus Seed Speech · Fast synchronous audio file

Provider source (opens in a new tab)
API model ID
volc.seedasr.auc_turbo

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
Fast synchronous audio fileSource for Service tier (opens in a new tab)
API aliases
request.model_name=bigmodelSource for API aliases (opens in a new tab)

The model resource header chooses the revision; bigmodel alone does not identify it.

Streaming
Not supportedSource for Streaming (opens in a new tab)
Audio duration limits
Up to 2 hoursSource for Audio duration limits (opens in a new tab)
Maximum audio file
At most 100 MBSource for Maximum audio file (opens in a new tab)
Reference images
One JPEG/JPG/PNG image, at most 500 KBSource for Reference images (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
TranscriptionInput audio1$0.36hour

Rate conditions

  1. Published ASR service-level PAYG rate for this processing mode. Optional concurrency and prepaid packages are separate; not a language-model token 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 · Bidirectional streaming

volc.seedasr.sauc.duration
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.

BytePlus Seed Speech · Asynchronous audio file

volc.seedasr.auc
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.

BytePlus Seed Speech · Fast synchronous audio file

volc.seedasr.auc_turbo
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