Streaming transcription, translated text and translated speech through a managed speech pipeline. DeepL supplies translation; selected speech languages use external service partners.
Recorded-file limit only. Live sessions are reconnectable, with a 30-second idle timeout and no fixed maximum duration in the reviewed live requirements.
match approximates the original voice only for DeepL-provided output languages; unsupported targets fall back to a preset without rejecting the session.
Billing basis
Audio playback duration at 1× speed, not socket time or accelerated transmission time. Voice service specification rounds fractional audio minutes upward.Source for Billing basis (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
Language API usage
Growth speech-to-text overage1
$1.85
additional source audio hour
Language API usage
Growth speech-to-speech overage2
$3.75
additional source audio hour
Rate conditions
Native India/USD price view, annual billing selected: Growth is $26/month billed annually, with 12M characters, 120 STT hours and 60 S2S hours per year. Usage above those allowances is extra. This is a shared account plan, not an extra subscription for every model/endpoint. 50M characters and 300 voice hours/month limits; Enterprise is custom. Native STT tariff. Voice specification rounds fractional audio minutes up; do not infer second-by-second billing from the hourly display.
Native India/USD price view, annual billing selected: Growth is $26/month billed annually, with 12M characters, 120 STT hours and 60 S2S hours per year. Usage above those allowances is extra. This is a shared account plan, not an extra subscription for every model/endpoint. 50M characters and 300 voice hours/month limits; Enterprise is custom. Native S2S tariff. Includes a different annual allowance from STT. Simultaneous target multipliers and stacking need account confirmation.
Paid Growth API advertises no data training. Terms allow temporary processing storage, encrypted exceptional debugging retention up to 72 hours, and metadata logs. Customer-requested stored content has separate deletion terms. Region is not universally fixed; enterprise residency requires agreement. Free Developer terms differ.
Endpoint pricing has not been collected. Check the provider for applicable rates.
Data & enterprise terms
Upload within 5 minutes of job creation and download results within 1 hour after upload. Results are marked for deletion when downloaded; once all are downloaded or the job expires, it is deleted and returns 404. General paid terms apply separately.
No public fixed model/checkpoint selector is documented.
Access
Marketplace contract for real-time voice transcription and text translation over WebSocket. The listed contract does not establish translated-audio entitlements.
Regions
Provider-managed; contractual residency options, no universal region pin
Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 13 Oct 2026
Category
Usage
Rate
Unit
Contract
Voice API Pro · 4,000 hours1
$11,400.00
12-month contract
Rate conditions
Vendor listing bundles 4,000 real-time transcription/translation hours. Not a standalone $/hour PAYG offer. Overage price and translated-audio rights are unverified; AWS AI Insights text is not treated as a vendor specification.
Paid Growth API advertises no data training. Terms allow temporary processing storage, encrypted exceptional debugging retention up to 72 hours, and metadata logs. Customer-requested stored content has separate deletion terms. Region is not universally fixed; enterprise residency requires agreement. Free Developer terms differ.
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.
DeepL API
Not verified
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
How it works
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
Minimum reusable input
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
Lifetime & refresh
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
How to enable it
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
Usage fields
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
Billing rules
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
Limits & data boundaries
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
DeepL API
Not verified
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
How it works
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
Minimum reusable input
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
Lifetime & refresh
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
How to enable it
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
Usage fields
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
Billing rules
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
Limits & data boundaries
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
DeepL Voice · AWS Marketplace
Not verified
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
How it works
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
Minimum reusable input
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
Lifetime & refresh
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
How to enable it
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
Usage fields
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
Billing rules
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model prompt caching.
Limits & data boundaries
Not collected
No discounted prompt-cache contract collected. Glossaries, translation memories, retained files and reconnectable sessions are not proof of model 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
DeepL terms identify proprietary models and restrict copying or reverse engineering of the service. This is a documented proprietary generation or explicitly identified managed/research family, not a claim that every hosted partner component is a DeepL checkpoint. Public model weights are not provided by the cited release or API documentation.
