Closed managed non-English transcription family with language-selected processing. The API exposes language choices, not a separate named checkpoint for every language.
57 non-English or mixed-language selectors after excluding three English selectors; locales and en/es are not 57 independently identified models. EU and streaming subsets differ.
Guide states 5 TB for source_config/dashboard, then says source_config has no file restriction. Both statements are retained as a conflict, not resolved by guessing.
No public standalone model/checkpoint selector; API version numbers are not model generations.
Access
Asynchronous transcription. Set language explicitly, or use language=auto with optional enable_multilingual. transcriber is ignored for non-English audio.
Guide states 5 TB for source_config/dashboard, then says source_config has no file restriction. Both statements are retained as a conflict, not resolved by guessing.
Diarization can be skipped; standard/premium options. Field-specific speaker count/channel controls name Spanish and French, with up to 8 channels; generic non-English restrictions conflict.Source for Speaker attribution (opens in a new tab)
Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 13 Oct 2026
Category
Usage
Rate
Unit
Speech usage
Foreign-language transcription1
$0.30
audio hour
Rate conditions
Current public PAYG tariff; rounded up to the next second with a 15-second minimum. Enterprise terms may differ. Free trial credit is finite, not an unlimited zero rate.
API jobs and associated files are retained for at most 30 days, with account/job deletion controls and manual deletion. An accounting record remains. Rev terms permit continuous training of its own ASR/AI models on speech-service content, while excluding generative-AI training. The security page’s external-LLM exclusion is not a universal no-training promise.
No public standalone model/checkpoint selector; API version numbers are not model generations.
Access
Asynchronous transcription. Set language explicitly, or use language=auto with optional enable_multilingual. transcriber is ignored for non-English audio.
Regions
EU: Frankfurt, Germany; separate deployment and account arrangements.
Guide states 5 TB for source_config/dashboard, then says source_config has no file restriction. Both statements are retained as a conflict, not resolved by guessing.
Diarization can be skipped; standard/premium options. Field-specific speaker count/channel controls name Spanish and French, with up to 8 channels; generic non-English restrictions conflict.Source for Speaker attribution (opens in a new tab)
Endpoint pricing has not been collected. Check the provider for applicable rates.
Data & enterprise terms
EU processing and storage in Frankfurt. EU language list differs. Deletion and training terms are separate from geographic residency; contact Rev for account configuration.
Bill the larger of wall-clock stream duration and submitted audio duration, with 15-second minimum. Initial hold: 10 minutes of credits; further 5-minute holds as the stream continues.Source for Billing basis (opens in a new tab)
No separately verified current streaming unit tariff is assigned from the asynchronous price label.
Endpoint pricing has not been collected. Check the provider for applicable rates.
Data & enterprise terms
delete_after_seconds accepts 0–2,592,000 seconds. Streaming docs state 0 means audio/transcript are never stored; nonzero deletion may lag by up to two minutes. This option does not establish a blanket no-training promise or erase accounting records.
Bill the larger of wall-clock stream duration and submitted audio duration, with 15-second minimum. Initial hold: 10 minutes of credits; further 5-minute holds as the stream continues.Source for Billing basis (opens in a new tab)
No separately verified current streaming unit tariff is assigned from the asynchronous price label.
Endpoint pricing has not been collected. Check the provider for applicable rates.
Data & enterprise terms
delete_after_seconds accepts 0–2,592,000 seconds. Streaming docs state 0 means audio/transcript are never stored; nonzero deletion may lag by up to two minutes. This option does not establish a blanket no-training promise or erase accounting records.
Bill the larger of wall-clock stream duration and submitted audio duration, with 15-second minimum. Initial hold: 10 minutes of credits; further 5-minute holds as the stream continues.Source for Billing basis (opens in a new tab)
No separately verified current streaming unit tariff is assigned from the asynchronous price label.
Endpoint pricing has not been collected. Check the provider for applicable rates.
Data & enterprise terms
delete_after_seconds accepts 0–2,592,000 seconds. Streaming docs state 0 means audio/transcript are never stored; nonzero deletion may lag by up to two minutes. This option does not establish a blanket no-training promise or erase accounting records.
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.
Rev AI API
Not verified
No model-specific discounted prompt-cache contract collected. Stored transcripts, reusable vocabularies and streaming sessions do not establish prompt caching.
How it works
Not collected
No model-specific discounted prompt-cache contract collected. Stored transcripts, reusable vocabularies and streaming sessions do not establish prompt caching.
Minimum reusable input
Not collected
No model-specific discounted prompt-cache contract collected. Stored transcripts, reusable vocabularies and streaming sessions do not establish prompt caching.
Lifetime & refresh
Not collected
No model-specific discounted prompt-cache contract collected. Stored transcripts, reusable vocabularies and streaming sessions do not establish prompt caching.
How to enable it
Not collected
No model-specific discounted prompt-cache contract collected. Stored transcripts, reusable vocabularies and streaming sessions do not establish prompt caching.
Usage fields
Not collected
No model-specific discounted prompt-cache contract collected. Stored transcripts, reusable vocabularies and streaming sessions do not establish prompt caching.
Billing rules
Not collected
No model-specific discounted prompt-cache contract collected. Stored transcripts, reusable vocabularies and streaming sessions do not establish prompt caching.
Limits & data boundaries
Not collected
No model-specific discounted prompt-cache contract collected. Stored transcripts, reusable vocabularies and streaming sessions do not establish prompt caching.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Rev AI API
Not verified
No model-specific discounted prompt-cache contract collected. Stored transcripts, reusable vocabularies and streaming sessions do not establish prompt caching.
How it works
Not collected
No model-specific discounted prompt-cache contract collected. Stored transcripts, reusable vocabularies and streaming sessions do not establish prompt caching.
Minimum reusable input
Not collected
No model-specific discounted prompt-cache contract collected. Stored transcripts, reusable vocabularies and streaming sessions do not establish prompt caching.
Lifetime & refresh
Not collected
No model-specific discounted prompt-cache contract collected. Stored transcripts, reusable vocabularies and streaming sessions do not establish prompt caching.
How to enable it
Not collected
No model-specific discounted prompt-cache contract collected. Stored transcripts, reusable vocabularies and streaming sessions do not establish prompt caching.
Usage fields
Not collected
No model-specific discounted prompt-cache contract collected. Stored transcripts, reusable vocabularies and streaming sessions do not establish prompt caching.
Billing rules
Not collected
No model-specific discounted prompt-cache contract collected. Stored transcripts, reusable vocabularies and streaming sessions do not establish prompt caching.
Limits & data boundaries
Not collected
No model-specific discounted prompt-cache contract collected. Stored transcripts, reusable vocabularies and streaming sessions do not establish prompt caching.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Rev AI API
Not verified
No model-specific discounted prompt-cache contract collected. Stored transcripts, reusable vocabularies and streaming sessions do not establish prompt caching.
How it works
Not collected
No model-specific discounted prompt-cache contract collected. Stored transcripts, reusable vocabularies and streaming sessions do not establish prompt caching.
Minimum reusable input
Not collected
No model-specific discounted prompt-cache contract collected. Stored transcripts, reusable vocabularies and streaming sessions do not establish prompt caching.
Lifetime & refresh
Not collected
No model-specific discounted prompt-cache contract collected. Stored transcripts, reusable vocabularies and streaming sessions do not establish prompt caching.
How to enable it
Not collected
No model-specific discounted prompt-cache contract collected. Stored transcripts, reusable vocabularies and streaming sessions do not establish prompt caching.
Usage fields
Not collected
No model-specific discounted prompt-cache contract collected. Stored transcripts, reusable vocabularies and streaming sessions do not establish prompt caching.
Billing rules
Not collected
No model-specific discounted prompt-cache contract collected. Stored transcripts, reusable vocabularies and streaming sessions do not establish prompt caching.
Limits & data boundaries
Not collected
No model-specific discounted prompt-cache contract collected. Stored transcripts, reusable vocabularies and streaming sessions do not establish prompt caching.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Rev AI API
Not verified
No model-specific discounted prompt-cache contract collected. Stored transcripts, reusable vocabularies and streaming sessions do not establish prompt caching.
How it works
Not collected
No model-specific discounted prompt-cache contract collected. Stored transcripts, reusable vocabularies and streaming sessions do not establish prompt caching.
Minimum reusable input
Not collected
No model-specific discounted prompt-cache contract collected. Stored transcripts, reusable vocabularies and streaming sessions do not establish prompt caching.
Lifetime & refresh
Not collected
No model-specific discounted prompt-cache contract collected. Stored transcripts, reusable vocabularies and streaming sessions do not establish prompt caching.
How to enable it
Not collected
No model-specific discounted prompt-cache contract collected. Stored transcripts, reusable vocabularies and streaming sessions do not establish prompt caching.
Usage fields
Not collected
No model-specific discounted prompt-cache contract collected. Stored transcripts, reusable vocabularies and streaming sessions do not establish prompt caching.
Billing rules
Not collected
No model-specific discounted prompt-cache contract collected. Stored transcripts, reusable vocabularies and streaming sessions do not establish prompt caching.
Limits & data boundaries
Not collected
No model-specific discounted prompt-cache contract collected. Stored transcripts, reusable vocabularies and streaming sessions do not establish prompt caching.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Rev AI API
Not verified
No model-specific discounted prompt-cache contract collected. Stored transcripts, reusable vocabularies and streaming sessions do not establish prompt caching.
How it works
Not collected
No model-specific discounted prompt-cache contract collected. Stored transcripts, reusable vocabularies and streaming sessions do not establish prompt caching.
Minimum reusable input
Not collected
No model-specific discounted prompt-cache contract collected. Stored transcripts, reusable vocabularies and streaming sessions do not establish prompt caching.
Lifetime & refresh
Not collected
No model-specific discounted prompt-cache contract collected. Stored transcripts, reusable vocabularies and streaming sessions do not establish prompt caching.
How to enable it
Not collected
No model-specific discounted prompt-cache contract collected. Stored transcripts, reusable vocabularies and streaming sessions do not establish prompt caching.
Usage fields
Not collected
No model-specific discounted prompt-cache contract collected. Stored transcripts, reusable vocabularies and streaming sessions do not establish prompt caching.
Billing rules
Not collected
No model-specific discounted prompt-cache contract collected. Stored transcripts, reusable vocabularies and streaming sessions do not establish prompt caching.
Limits & data boundaries
Not collected
No model-specific discounted prompt-cache contract collected. Stored transcripts, reusable vocabularies and streaming sessions 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
Rev reserves its proprietary services and model technology and prohibits copying or reverse engineering. This record covers legacy proprietary ASR or an explicitly labeled managed API family/option whose internal checkpoint is not published. The separately downloadable English Reverb ASR and diarization releases are excluded; API billing alone is not proof of closed weights.
