Whisper Large v3 Turbo
OpenAI · released Oct 1, 2024 · openai/whisper-large-v3-turbo
Speech to textTranscribes a recording into words
- Type
- Open weightsMIT License
- Languages
- 99
- Size
- 0.8B
Context measured in tokens
Our take
Written Aug 3, 2026Whisper Large v3 Turbo is a compact downloadable speech-to-text model from OpenAI that turns audio into written words at exceptional speed. It carries a permissive MIT licence and handles 99 claimed languages, though every accuracy figure we hold is English-only.
Pick this for high-throughput transcription where speed beats perfection — it processes an hour of audio in under five seconds. Use it for clean recordings like read-aloud text or financial calls, with under three words wrong per hundred. Skip it if your audio is messy: meetings, podcasts or accented speech push errors past one in ten words, or if you need verified non-English accuracy.
The case for it
- Extremely fast transcription: roughly an hour of audio in about four and a half seconds on benchmark hardware.
- Very low error rate on clean, structured audio: about two words wrong per hundred on read-aloud speech, under three on financial calls.
- Truly permissive MIT licence allows commercial use, modification and redistribution.
- Broad claimed language coverage: 99 languages listed, including major world languages.
The case against it
- Accuracy collapses on challenging real-world audio: recorded meetings see more than six times the error rate of clean read speech.
- Even slightly harder read-aloud audio degrades sharply — a 74 percent relative increase in errors against the cleanest recordings.
- Every accuracy figure here is English; nothing we hold measures the other 98 claimed languages.
How good is it?
TranscriptionTurning speech into text2 of 5Open ASR WER · 61st of 74
93%
Misses roughly one word in 14, averaged over nine English test sets.
783×29th of 62
an hour of audio in 5 seconds, on the board's own hardware. Your machine will differ.
99
Listed on the model card. The accuracy above is English only.
Percentage of words wrong on each set, lower better. Bars are scaled to this model's own worst case, not to the board.
Which languages ↓ ↑
English · Chinese · German · Spanish · Russian · Korean · French · Japanese · Portuguese · Turkish · Polish · Catalan · Dutch · Arabic · Swedish · Italian · Indonesian · Hindi · Finnish · Vietnamese · Hebrew · Ukrainian · Greek · Malay · Czech · Romanian · Danish · Hungarian · Tamil · Norwegian · Thai · Urdu · Croatian · Bulgarian · Lithuanian · Latin · Māori · Malayalam · Welsh · Slovak · Telugu · Persian · Latvian · Bangla · Serbian · Azerbaijani · Slovenian · Kannada · Estonian · Macedonian · Breton · Basque · Icelandic · Armenian · Nepali · Mongolian · Bosnian · Kazakh · Albanian · Swahili · Galician · Marathi · Punjabi · Sinhala · Khmer · Shona · Yoruba · Somali · Afrikaans · Occitan · Georgian · Belarusian · Tajik · Sindhi · Gujarati · Amharic · Yiddish · Lao · Uzbek · Faroese · Haitian Creole · Pashto · Turkmen · Norwegian Nynorsk · Maltese · Sanskrit · Luxembourgish · Burmese · bo · Filipino · Malagasy · Assamese · Tatar · Hawaiian · Lingala · Hausa · ba · Javanese · Sundanese
The figures above come from the Open ASR Leaderboard, an independent public test that runs every model on the same recordings. It is the only measurement of transcription quality we know of, so there are no other scores to show.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done, which is why they get no rating.
Every published score for this model9 scoresEvery figure we hold, from 9 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Can you run it yourself?
- Fits in memory
- weights load entirely on the card
- Spills to system RAM
- some weights offload; much slower
- Too large
- will not load even with offload
- est
- size is calculated; the verdict could change by 10%
Comfortable fit
GeForce RTX 4090 · 24 GB
Room to spare. 21.1 GB spare means a 10% error in the size would not change the answer.
Apple M1 Pro (16-core GPU) · 32 GB
Room to spare. 22.3 GB spare means a 10% error in the size would not change the answer.
Apple M2 (8-core GPU, 8GB unified) · 8 GB
Room to spare. 4.3 GB spare means a 10% error in the size would not change the answer.
Memory use by level
Against a 24 GB card.
All 3 sizes here are calculated, not measured. We hold no measured file for this model, so each size comes from the parameter count and every verdict above inherits that uncertainty.
Check against your own machine → · All 71 devices, with every size →
Or rent it from someone else
Cheapest of 2 live listings. Picked at the widest standard context we hold, within one quantisation slice, so the numbers beside it are a price one host actually charges.
- per minute of audio
- $0.001
- Context served
- —
- Throughput
- Not measured
| Provider | Price per minute of audio | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| Groq | $0.001 | not reported | not measured | Unknown | Unknown | Unknown |
| IBM watsonx | $0.006 | not reported | not measured | Unknown | Unknown | Unknown |
Across the 2 listings we hold: 0 say they do not train on prompts, 0 say they do and 2 do not say. 0 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
When we formed this view
Dates behind this page
Prices last checked 6h ago
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- 2 of 2 listings publish no parameter list, so what their API accepts is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 2 of 2 listings do not say whether they train on prompts.
- We hold no cached-input rate for any of its listings.
Licence and identifiers
What the licence allowsMIT License, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
MIT License
Fully permissive: do anything with attribution. No patent grant, unlike Apache-2.0.
Identifiers
- Hugging Face
- openai/whisper-large-v3-turbo
- Architecture
- Dense
- Modality record
- audio->text
- Catalogue slug
- openai-whisper-large-v3-turbo