Skip to content
Model infoModelsSnapshot: 15 Oct 2026

ByteDance / Seed Live Interpretation

Seed Live Interpretation

Live speech translation to text or speech, with output voice selection governed by the hosting API.

Speech & voice
availableClosed weightsSpeech-to-speechTranslation
Official documentation (opens in a new tab)Reviewed 15 Oct 2026
7 of 18 specification fields collected
Context windowNot collectedAwaiting source review
Maximum outputNot collectedAwaiting source review
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
AudioSource for Input modalities (opens in a new tab)
Output modalities
Audio, 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
End-to-end speech understanding and translation modelSource for Architecture (opens in a new tab)
Languages
View all 22 entries
  • Chinese
  • English
  • Portuguese
  • Spanish
  • Japanese
  • Indonesian
  • German
  • French
  • Russian
  • Italian
  • Korean
  • Arabic
  • Turkish
  • Malay
  • Vietnamese
  • Thai
  • Dutch
  • Romanian
  • Polish
  • Czech
  • Cantonese (source only)
  • Shanghainese (source only)
Source for Languages (opens in a new tab)

For S2T one side of the pair must be Chinese or English. S2S additionally requires a compatible TTS/ICL voice.

Context caching
Not collected
Audio formats
PCM, OGG_OPUSSource for Audio formats (opens in a new tab)
Audio sample rates
PCM output: 16 or 24 kHz; OGG_OPUS output: fixed 48 kHzSource for Audio sample rates (opens in a new tab)

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 · Realtime WebSocket S2T / S2S

Provider source (opens in a new tab)
API model ID
volc.service_type.1000025

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
Realtime WebSocket S2T / S2SSource for Service tier (opens in a new tab)
API endpoint URL
wss://voice.ap-southeast-1.bytepluses.com/api/v4/ast/v2/translateSource for API endpoint URL (opens in a new tab)
Input audio format
Mono PCM-encoded WAV, 16 kHz, 16-bitSource for Input audio format (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Live interpretationInput audio1$12.001M input audio tokens
Live interpretationOutput audio1$46.001M output audio tokens
Live interpretationOutput text1$12.001M text tokens

Rate conditions

  1. Published PAYG schedule. Provider approximates 6.25 input audio tokens/second and 25 output audio tokens/second. Do not treat audio tokens as text tokens; external-voice charges require confirmation.
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 · Realtime WebSocket S2T / S2S

volc.service_type.1000025
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