Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Soniox / Soniox STT

STT v5 Async

Multilingual speech recognition with speaker separation, contextual vocabulary and optional translation.

availableClosed weightsTranscriptionSpeech translation
Official documentation (opens in a new tab)Reviewed 13 Oct 2026
10 of 21 specification fields collected
Audio durationUp to 300 minutes of audioSee specification notes below
Audio formatsNot collectedAwaiting source review
Input billingSee ratesSoniox API
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 contextSource for Input 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)

Async file transcription; polling a queued job is not streaming inference.

Batch processing
Not collected
Fine-tuning
Not collected
Knowledge cutoff
Not collected
Parameters
Not collected
Architecture
Not collected
Languages
View all 60 entries
  • Afrikaans (af)
  • Albanian (sq)
  • Arabic (ar)
  • Azerbaijani (az)
  • Basque (eu)
  • Belarusian (be)
  • Bengali (bn)
  • Bosnian (bs)
  • Bulgarian (bg)
  • Catalan (ca)
  • Chinese (zh)
  • Croatian (hr)
  • Czech (cs)
  • Danish (da)
  • Dutch (nl)
  • English (en)
  • Estonian (et)
  • Finnish (fi)
  • French (fr)
  • Galician (gl)
  • German (de)
  • Greek (el)
  • Gujarati (gu)
  • Hebrew (he)
  • Hindi (hi)
  • Hungarian (hu)
  • Indonesian (id)
  • Italian (it)
  • Japanese (ja)
  • Kannada (kn)
  • Kazakh (kk)
  • Korean (ko)
  • Latvian (lv)
  • Lithuanian (lt)
  • Macedonian (mk)
  • Malay (ms)
  • Malayalam (ml)
  • Marathi (mr)
  • Norwegian (no)
  • Persian (fa)
  • Polish (pl)
  • Portuguese (pt)
  • Punjabi (pa)
  • Romanian (ro)
  • Russian (ru)
  • Serbian (sr)
  • Slovak (sk)
  • Slovenian (sl)
  • Spanish (es)
  • Swahili (sw)
  • Swedish (sv)
  • Tagalog (tl)
  • Tamil (ta)
  • Telugu (te)
  • Thai (th)
  • Turkish (tr)
  • Ukrainian (uk)
  • Urdu (ur)
  • Vietnamese (vi)
  • Welsh (cy)
Source for Languages (opens in a new tab)
Context caching
Not collected
Audio duration limits
Up to 300 minutes of audioSource for Audio duration limits (opens in a new tab)
Required request fields
Audio plus optional language hints, speaker diarization, language identification and structured contextSource for Required request fields (opens in a new tab)
Supplied context limit
8,000 context tokens, approximately 10,000 charactersSource for Supplied context limit (opens in a new tab)

Limit for supplied context; not a combined audio/text model context window.

Published price
Input audio $1.50/M; input text context $3.50/M; output text $3.50/M tokensSource for Published price (opens in a new tab)
Usage metering
About $0.10/hour for typical transcription; actual billing uses modality-specific tokensSource for Usage metering (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.

API model ID
stt-async-v5
Access
API key and available balance required. Regional projects require matching region-specific keys and endpoint domains.
Regions
United States
API endpoint URL
https://api.soniox.com/v1/transcriptionsSource for API endpoint URL (opens in a new tab)
Equivalent API aliases
stt-async-v4Source for Equivalent API aliases (opens in a new tab)

These older IDs now invoke v5, not the original v4 weights. Earlier redirects are retained on their historical records rather than assumed to be permanent current aliases.

Audio duration limits
Up to 300 minutes of audioSource for Audio duration limits (opens in a new tab)
Supplied context limit
8,000 context tokens, approximately 10,000 charactersSource for Supplied context limit (opens in a new tab)

Limit for supplied context; not a combined audio/text model context window.

Streaming
Not supportedSource for Streaming (opens in a new tab)

Async file transcription; polling a queued job is not streaming inference.

Required request fields
Audio plus optional language hints, speaker diarization, language identification and structured contextSource for Required request fields (opens in a new tab)
Request mode
One audio_url or uploaded file_id; completion via polling or webhookSource for Request mode (opens in a new tab)
Request quotas
Default: 100 pending transcriptions, 2,000 total jobs, 1,000 files and 10 GB aggregate storageSource for Request quotas (opens in a new tab)
Regional processing
Content processing/storage stays in the project region; account, billing and system metadata are excludedSource for Regional processing (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Speech APIInput audio1$1.501M audio tokens
Speech APIInput text context1$3.501M text tokens
Speech APIOutput text1$3.501M text tokens

Rate conditions

  1. Published modality-specific token rate. Hourly equivalents on the pricing page are illustrative, not separate flat charges. Text context and translated output contribute to usage. Regional enterprise agreements may differ; these are public list rates. No generic text-question estimate.
Pricing source (opens in a new tab)

Data & enterprise terms

Provider states submitted content is not used to train or improve models. Real-time audio/transcript content is not retained; async files and transcripts are stored, deletable by the customer and automatically removed after 30 days. Operational usage metadata is retained. Regional residency excludes account, billing and other system data.

Read the service policy (opens in a new tab)
API model ID
stt-async-v5
Access
API key and available balance required. Regional projects require matching region-specific keys and endpoint domains.
Regions
European Union
API endpoint URL
https://api.eu.soniox.com/v1/transcriptionsSource for API endpoint URL (opens in a new tab)
Equivalent API aliases
stt-async-v4Source for Equivalent API aliases (opens in a new tab)

These older IDs now invoke v5, not the original v4 weights. Earlier redirects are retained on their historical records rather than assumed to be permanent current aliases.

Audio duration limits
Up to 300 minutes of audioSource for Audio duration limits (opens in a new tab)
Supplied context limit
8,000 context tokens, approximately 10,000 charactersSource for Supplied context limit (opens in a new tab)

Limit for supplied context; not a combined audio/text model context window.

Streaming
Not supportedSource for Streaming (opens in a new tab)

Async file transcription; polling a queued job is not streaming inference.

Required request fields
Audio plus optional language hints, speaker diarization, language identification and structured contextSource for Required request fields (opens in a new tab)
Request mode
One audio_url or uploaded file_id; completion via polling or webhookSource for Request mode (opens in a new tab)
Request quotas
Default: 100 pending transcriptions, 2,000 total jobs, 1,000 files and 10 GB aggregate storageSource for Request quotas (opens in a new tab)
Regional processing
Content processing/storage stays in the project region; account, billing and system metadata are excludedSource for Regional processing (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Speech APIInput audio1$1.501M audio tokens
Speech APIInput text context1$3.501M text tokens
Speech APIOutput text1$3.501M text tokens

Rate conditions

  1. Published modality-specific token rate. Hourly equivalents on the pricing page are illustrative, not separate flat charges. Text context and translated output contribute to usage. Regional enterprise agreements may differ; these are public list rates. No generic text-question estimate.
Pricing source (opens in a new tab)

Data & enterprise terms

Provider states submitted content is not used to train or improve models. Real-time audio/transcript content is not retained; async files and transcripts are stored, deletable by the customer and automatically removed after 30 days. Operational usage metadata is retained. Regional residency excludes account, billing and other system data.

Read the service policy (opens in a new tab)
API model ID
stt-async-v5
Access
API key and available balance required. Regional projects require matching region-specific keys and endpoint domains.
Regions
Japan
API endpoint URL
https://api.jp.soniox.com/v1/transcriptionsSource for API endpoint URL (opens in a new tab)
Equivalent API aliases
stt-async-v4Source for Equivalent API aliases (opens in a new tab)

These older IDs now invoke v5, not the original v4 weights. Earlier redirects are retained on their historical records rather than assumed to be permanent current aliases.

Audio duration limits
Up to 300 minutes of audioSource for Audio duration limits (opens in a new tab)
Supplied context limit
8,000 context tokens, approximately 10,000 charactersSource for Supplied context limit (opens in a new tab)

Limit for supplied context; not a combined audio/text model context window.

Streaming
Not supportedSource for Streaming (opens in a new tab)

Async file transcription; polling a queued job is not streaming inference.

Required request fields
Audio plus optional language hints, speaker diarization, language identification and structured contextSource for Required request fields (opens in a new tab)
Request mode
One audio_url or uploaded file_id; completion via polling or webhookSource for Request mode (opens in a new tab)
Request quotas
Default: 100 pending transcriptions, 2,000 total jobs, 1,000 files and 10 GB aggregate storageSource for Request quotas (opens in a new tab)
Regional processing
Content processing/storage stays in the project region; account, billing and system metadata are excludedSource for Regional processing (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Speech APIInput audio1$1.501M audio tokens
Speech APIInput text context1$3.501M text tokens
Speech APIOutput text1$3.501M text tokens

Rate conditions

  1. Published modality-specific token rate. Hourly equivalents on the pricing page are illustrative, not separate flat charges. Text context and translated output contribute to usage. Regional enterprise agreements may differ; these are public list rates. No generic text-question estimate.
Pricing source (opens in a new tab)

Data & enterprise terms

Provider states submitted content is not used to train or improve models. Real-time audio/transcript content is not retained; async files and transcripts are stored, deletable by the customer and automatically removed after 30 days. Operational usage metadata is retained. Regional residency excludes account, billing and other system data.

Read the service policy (opens in a new tab)
API model ID
stt-async-v5
Access
API key and available balance required. Regional projects require matching region-specific keys and endpoint domains.
Regions
India
API endpoint URL
https://api.in.soniox.com/v1/transcriptionsSource for API endpoint URL (opens in a new tab)
Equivalent API aliases
stt-async-v4Source for Equivalent API aliases (opens in a new tab)

These older IDs now invoke v5, not the original v4 weights. Earlier redirects are retained on their historical records rather than assumed to be permanent current aliases.

Audio duration limits
Up to 300 minutes of audioSource for Audio duration limits (opens in a new tab)
Supplied context limit
8,000 context tokens, approximately 10,000 charactersSource for Supplied context limit (opens in a new tab)

Limit for supplied context; not a combined audio/text model context window.

Streaming
Not supportedSource for Streaming (opens in a new tab)

Async file transcription; polling a queued job is not streaming inference.

Required request fields
Audio plus optional language hints, speaker diarization, language identification and structured contextSource for Required request fields (opens in a new tab)
Request mode
One audio_url or uploaded file_id; completion via polling or webhookSource for Request mode (opens in a new tab)
Request quotas
Default: 100 pending transcriptions, 2,000 total jobs, 1,000 files and 10 GB aggregate storageSource for Request quotas (opens in a new tab)
Regional processing
Content processing/storage stays in the project region; account, billing and system metadata are excludedSource for Regional processing (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Speech APIInput audio1$1.501M audio tokens
Speech APIInput text context1$3.501M text tokens
Speech APIOutput text1$3.501M text tokens

Rate conditions

  1. Published modality-specific token rate. Hourly equivalents on the pricing page are illustrative, not separate flat charges. Text context and translated output contribute to usage. Regional enterprise agreements may differ; these are public list rates. No generic text-question estimate.
Pricing source (opens in a new tab)

Data & enterprise terms

Provider states submitted content is not used to train or improve models. Real-time audio/transcript content is not retained; async files and transcripts are stored, deletable by the customer and automatically removed after 30 days. Operational usage metadata is retained. Regional residency excludes account, billing and other system data.

Read the service policy (opens in a new tab)

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.

Soniox API

stt-async-v5
Not verified

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

How it works
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Minimum reusable input
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Lifetime & refresh
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

How to enable it
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Usage fields
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Billing rules
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Limits & data boundaries
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

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

Soniox API

stt-async-v5
Not verified

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

How it works
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Minimum reusable input
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Lifetime & refresh
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

How to enable it
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Usage fields
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Billing rules
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Limits & data boundaries
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

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

Soniox API

stt-async-v5
Not verified

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

How it works
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Minimum reusable input
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Lifetime & refresh
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

How to enable it
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Usage fields
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Billing rules
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Limits & data boundaries
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

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

Soniox API

stt-async-v5
Not verified

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

How it works
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Minimum reusable input
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Lifetime & refresh
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

How to enable it
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Usage fields
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Billing rules
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Limits & data boundaries
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

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

The provider identifies its hosted models as Soniox intellectual property, grants limited service access and prohibits extraction/reverse engineering. Native release documentation and historical reports establish these model identities; no public weight license is inferred from SDK availability.

Classification evidence (opens in a new tab)

Lifecycle dates

Model release11 Jun 2026Source (opens in a new tab)

Sources reviewed