OpenAI: Whisper Large V3 Turbo
Whisper Large V3 Turbo is an optimized version of OpenAI's Whisper Large V3 speech recognition model, designed for speed and cost efficiency. It supports transcription across 99+ languages with a 12%…
openai/whisper-large-v3-turbo
Whisper Large V3 Turbo is an optimized version of OpenAI's Whisper Large V3 speech recognition model, designed for speed and cost efficiency. It supports transcription across 99+ languages with a 12% word error rate, and accepts common audio formats including mp3, mp4, wav, webm, flac, and ogg. Achieves real-time speed factors up to 216x, making it well-suited for latency-sensitive and high-throughput transcription workloads.
Specifications & capabilities
- Input
- audio
- Output
- transcription
- Context window · tokens
- 0
- Published model ID
- whisper-large-v3-turbo
- Capabilities
- audioInput
Description source ↗Evaluations
1–20 / 116
251.74
- source id
- openASR
- leaderboard name
- RTFx
- dimension
- runtime
- metric
- RTFx
- rank
- 5
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- hf-audio/multilingual_evals/multilingual_hi.csv
- metric_method
- published WER/RTFx
- metric_kind
- RTFx
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- hf-audio/multilingual_evals/multilingual_hi.csv
- published_at
- 2026-10-21T14:20:31Z
- source_revision
- 943867e1b478153a2161b0522c130917d0d96b01a780660e00252b573bc2cf13
- metric_population
- 21
- benchmark_evaluation
- true
- source model id
- openai/whisper-large-v3-turbo
Original result ↗974.13
- source id
- openASR
- leaderboard name
- RTFx
- dimension
- runtime
- metric
- RTFx
- rank
- 6
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- hf-audio/multilingual_evals/multilingual_pt.csv
- metric_method
- published WER/RTFx
- metric_kind
- RTFx
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- hf-audio/multilingual_evals/multilingual_pt.csv
- published_at
- 2026-10-21T14:20:31Z
- source_revision
- 943867e1b478153a2161b0522c130917d0d96b01a780660e00252b573bc2cf13
- metric_population
- 27
- benchmark_evaluation
- true
- source model id
- openai/whisper-large-v3-turbo
Original result ↗148.26
- source id
- openASR
- leaderboard name
- RTFx
- dimension
- runtime
- metric
- RTFx
- rank
- 6
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- hf-audio/leaderboard_longform/longform_latest.csv
- metric_method
- published WER/RTFx
- metric_kind
- RTFx
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- hf-audio/leaderboard_longform/longform_latest.csv
- published_at
- 2026-10-21T14:20:31Z
- source_revision
- 943867e1b478153a2161b0522c130917d0d96b01a780660e00252b573bc2cf13
- metric_population
- 8
- benchmark_evaluation
- true
- source model id
- openai/whisper-large-v3-turbo
Original result ↗608.53
- source id
- openASR
- leaderboard name
- RTFx
- dimension
- runtime
- metric
- RTFx
- rank
- 8
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- hf-audio/multilingual_evals/multilingual_nl.csv
- metric_method
- published WER/RTFx
- metric_kind
- RTFx
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- hf-audio/multilingual_evals/multilingual_nl.csv
- published_at
- 2026-10-21T14:20:31Z
- source_revision
- 943867e1b478153a2161b0522c130917d0d96b01a780660e00252b573bc2cf13
- metric_population
- 24
- benchmark_evaluation
- true
- source model id
- openai/whisper-large-v3-turbo
Original result ↗373.78
- source id
- openASR
- leaderboard name
- Long-form · RTFx
- dimension
- runtime
- metric
- Long-form · RTFx
- rank
- 8
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- view
- longform
- suite
- OpenASR official public table
- datasets
- Earnings21
- Earnings22
- CORAAL
- metric_method
- publisher WER/RTFx for selected public view
- space_revision
- 3b5317f4e49b6cb40502b95065b29fbfe08284ce
- publisher_version
- 13-11-2026
- metric_kind
- Long-form · RTFx
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- public/longform.json
- published_at
- 2026-11-13T11:42:34Z
- source_revision
- 8f2cc9c9f3b01b8670c8640efc67f24a3ea076c2bf5e90e7c674a1a829d69bd7
- metric_population
- 10
- benchmark_evaluation
- true
- source model id
- openai/whisper-large-v3-turbo 🤗
Original result ↗13.1%
- source id
- openASR
- leaderboard name
- earnings22 (WER)
- dimension
- speech
- metric
- earnings22 (WER)
- rank
- 8
- aggregation scope
- status
- published
- direction
- lowerIsBetter
- conditions
- suite
- hf-audio/leaderboard_longform/longform_latest.csv
- metric_method
- published WER/RTFx
- metric_kind
- earnings22 (WER)
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- hf-audio/leaderboard_longform/longform_latest.csv
- published_at
- 2026-10-21T14:20:31Z
- source_revision
- 943867e1b478153a2161b0522c130917d0d96b01a780660e00252b573bc2cf13
- metric_population
- 16
- benchmark_evaluation
- true
- source model id
- openai/whisper-large-v3-turbo
Original result ↗12.82%
- source id
- openASR
- leaderboard name
- Long-form · Average WER
- dimension
- speech
- metric
- Long-form · Average WER
- rank
- 9
- aggregation scope
- status
- published
- direction
- lowerIsBetter
- conditions
- view
- longform
- suite
- OpenASR official public table
- datasets
- Earnings21
- Earnings22
- CORAAL
- metric_method
- publisher WER/RTFx for selected public view
- space_revision
- 3b5317f4e49b6cb40502b95065b29fbfe08284ce
- publisher_version
- 13-11-2026
- metric_kind
- Long-form · Average WER
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- public/longform.json
- published_at
- 2026-11-13T11:42:34Z
- source_revision
- 8f2cc9c9f3b01b8670c8640efc67f24a3ea076c2bf5e90e7c674a1a829d69bd7
- metric_population
- 14
- benchmark_evaluation
- true
- source model id
- openai/whisper-large-v3-turbo 🤗
Original result ↗9.28%
- source id
- openASR
- leaderboard name
- Long-form · Earnings21 (WER)
- dimension
- speech
- metric
- Long-form · Earnings21 (WER)
- rank
- 9
- aggregation scope
- status
- published
- direction
- lowerIsBetter
- conditions
- view
- longform
- suite
- OpenASR official public table
- datasets
- Earnings21
- Earnings22
- CORAAL
- metric_method
- publisher WER/RTFx for selected public view
- space_revision
- 3b5317f4e49b6cb40502b95065b29fbfe08284ce
- publisher_version
- 13-11-2026
- metric_kind
- Long-form · Earnings21 (WER)
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- public/longform.json
- published_at
- 2026-11-13T11:42:34Z
- source_revision
- 8f2cc9c9f3b01b8670c8640efc67f24a3ea076c2bf5e90e7c674a1a829d69bd7
- metric_population
- 14
- benchmark_evaluation
- true
- source model id
- openai/whisper-large-v3-turbo 🤗
Original result ↗8.723%
- source id
- openASR
- leaderboard name
- Avg (without CORAAL) (WER)
- dimension
- speech
- metric
- Avg (without CORAAL) (WER)
- rank
- 9
- aggregation scope
- status
- published
- direction
- lowerIsBetter
- conditions
- suite
- hf-audio/leaderboard_longform/longform_latest.csv
- metric_method
- published WER/RTFx
- metric_kind
- Avg (without CORAAL) (WER)
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- hf-audio/leaderboard_longform/longform_latest.csv
- published_at
- 2026-10-21T14:20:31Z
- source_revision
- 943867e1b478153a2161b0522c130917d0d96b01a780660e00252b573bc2cf13
- metric_population
- 16
- benchmark_evaluation
- true
- source model id
- openai/whisper-large-v3-turbo
Original result ↗5.55%
- source id
- openASR
- leaderboard name
- pt_mls (WER)
- dimension
- speech
- metric
- pt_mls (WER)
- rank
- 9
- aggregation scope
- status
- published
- direction
- lowerIsBetter
- conditions
- suite
- hf-audio/multilingual_evals/multilingual_latest.csv
- metric_method
- published WER/RTFx
- metric_kind
- pt_mls (WER)
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- hf-audio/multilingual_evals/multilingual_latest.csv
- published_at
- 2026-10-21T14:20:31Z
- source_revision
- 943867e1b478153a2161b0522c130917d0d96b01a780660e00252b573bc2cf13
- metric_population
- 34
- benchmark_evaluation
- true
- source model id
- openai/whisper-large-v3-turbo
Original result ↗2.7%
- source id
- openASR
- leaderboard name
- es_fleurs (WER)
- dimension
- speech
- metric
- es_fleurs (WER)
- rank
- 9
- aggregation scope
- status
- published
- direction
- lowerIsBetter
- conditions
- suite
- hf-audio/multilingual_evals/multilingual_latest.csv
- metric_method
- published WER/RTFx
- metric_kind
- es_fleurs (WER)
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- hf-audio/multilingual_evals/multilingual_latest.csv
- published_at
- 2026-10-21T14:20:31Z
- source_revision
- 943867e1b478153a2161b0522c130917d0d96b01a780660e00252b573bc2cf13
- metric_population
- 34
- benchmark_evaluation
- true
- source model id
- openai/whisper-large-v3-turbo
Original result ↗660.78
- source id
- openASR
- leaderboard name
- RTFx
- dimension
- runtime
- metric
- RTFx
- rank
- 10
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- hf-audio/multilingual_evals/multilingual_es.csv
- metric_method
- published WER/RTFx
- metric_kind
- RTFx
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- hf-audio/multilingual_evals/multilingual_es.csv
- published_at
- 2026-10-21T14:20:31Z
- source_revision
- 943867e1b478153a2161b0522c130917d0d96b01a780660e00252b573bc2cf13
- metric_population
- 27
- benchmark_evaluation
- true
- source model id
- openai/whisper-large-v3-turbo
Original result ↗591.2
- source id
- openASR
- leaderboard name
- RTFx
- dimension
- runtime
- metric
- RTFx
- rank
- 10
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- hf-audio/multilingual_evals/multilingual_fr.csv
- metric_method
- published WER/RTFx
- metric_kind
- RTFx
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- hf-audio/multilingual_evals/multilingual_fr.csv
- published_at
- 2026-10-21T14:20:31Z
- source_revision
- 943867e1b478153a2161b0522c130917d0d96b01a780660e00252b573bc2cf13
- metric_population
- 27
- benchmark_evaluation
- true
- source model id
- openai/whisper-large-v3-turbo
Original result ↗423
- source id
- openASR
- leaderboard name
- RTFx
- dimension
- runtime
- metric
- RTFx
- rank
- 10
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- hf-audio/multilingual_evals/multilingual_it.csv
- metric_method
- published WER/RTFx
- metric_kind
- RTFx
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- hf-audio/multilingual_evals/multilingual_it.csv
- published_at
- 2026-10-21T14:20:31Z
- source_revision
- 943867e1b478153a2161b0522c130917d0d96b01a780660e00252b573bc2cf13
- metric_population
- 26
- benchmark_evaluation
- true
- source model id
- openai/whisper-large-v3-turbo
Original result ↗176.16
- source id
- openASR
- leaderboard name
- RTFx
- dimension
- runtime
- metric
- RTFx
- rank
- 10
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- hf-audio/multilingual_evals/multilingual_latest.csv
- metric_method
- published WER/RTFx
- metric_kind
- RTFx
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- hf-audio/multilingual_evals/multilingual_latest.csv
- published_at
- 2026-10-21T14:20:31Z
- source_revision
- 943867e1b478153a2161b0522c130917d0d96b01a780660e00252b573bc2cf13
- metric_population
- 27
- benchmark_evaluation
- true
- source model id
- openai/whisper-large-v3-turbo
Original result ↗12.64%
- source id
- openASR
- leaderboard name
- Long-form · Earnings22 (WER)
- dimension
- speech
- metric
- Long-form · Earnings22 (WER)
- rank
- 10
- aggregation scope
- status
- published
- direction
- lowerIsBetter
- conditions
- view
- longform
- suite
- OpenASR official public table
- datasets
- Earnings21
- Earnings22
- CORAAL
- metric_method
- publisher WER/RTFx for selected public view
- space_revision
- 3b5317f4e49b6cb40502b95065b29fbfe08284ce
- publisher_version
- 13-11-2026
- metric_kind
- Long-form · Earnings22 (WER)
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- public/longform.json
- published_at
- 2026-11-13T11:42:34Z
- source_revision
- 8f2cc9c9f3b01b8670c8640efc67f24a3ea076c2bf5e90e7c674a1a829d69bd7
- metric_population
- 14
- benchmark_evaluation
- true
- source model id
- openai/whisper-large-v3-turbo 🤗
Original result ↗11.01%
- source id
- openASR
- leaderboard name
- Average (WER)
- dimension
- speech
- metric
- Average (WER)
- rank
- 10
- aggregation scope
- status
- published
- direction
- lowerIsBetter
- conditions
- suite
- hf-audio/leaderboard_longform/longform_latest.csv
- metric_method
- published WER/RTFx
- metric_kind
- Average (WER)
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- hf-audio/leaderboard_longform/longform_latest.csv
- published_at
- 2026-10-21T14:20:31Z
- source_revision
- 943867e1b478153a2161b0522c130917d0d96b01a780660e00252b573bc2cf13
- metric_population
- 16
- benchmark_evaluation
- true
- source model id
- openai/whisper-large-v3-turbo
Original result ↗974.13
- source id
- openASR
- leaderboard name
- 🇵🇹 Portuguese · RTFx
- dimension
- runtime
- metric
- 🇵🇹 Portuguese · RTFx
- rank
- 11
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- view
- multilingual/portuguese
- suite
- OpenASR official public table
- metric_method
- publisher WER/RTFx for selected public view
- space_revision
- 3b5317f4e49b6cb40502b95065b29fbfe08284ce
- publisher_version
- 13-11-2026
- metric_kind
- 🇵🇹 Portuguese · RTFx
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- public/multilingual/portuguese.json
- published_at
- 2026-11-13T11:42:34Z
- source_revision
- 8f2cc9c9f3b01b8670c8640efc67f24a3ea076c2bf5e90e7c674a1a829d69bd7
- metric_population
- 33
- benchmark_evaluation
- true
- source model id
- openai/whisper-large-v3-turbo 🤗
Original result ↗16.54%
- source id
- openASR
- leaderboard name
- Long-form · CORAAL (WER)
- dimension
- speech
- metric
- Long-form · CORAAL (WER)
- rank
- 11
- aggregation scope
- status
- published
- direction
- lowerIsBetter
- conditions
- view
- longform
- suite
- OpenASR official public table
- datasets
- Earnings21
- Earnings22
- CORAAL
- metric_method
- publisher WER/RTFx for selected public view
- space_revision
- 3b5317f4e49b6cb40502b95065b29fbfe08284ce
- publisher_version
- 13-11-2026
- metric_kind
- Long-form · CORAAL (WER)
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- public/longform.json
- published_at
- 2026-11-13T11:42:34Z
- source_revision
- 8f2cc9c9f3b01b8670c8640efc67f24a3ea076c2bf5e90e7c674a1a829d69bd7
- metric_population
- 14
- benchmark_evaluation
- true
- source model id
- openai/whisper-large-v3-turbo 🤗
Original result ↗5.03%
- source id
- openASR
- leaderboard name
- MLS WER (WER)
- dimension
- speech
- metric
- MLS WER (WER)
- rank
- 11
- aggregation scope
- status
- published
- direction
- lowerIsBetter
- conditions
- suite
- hf-audio/multilingual_evals/multilingual_nl.csv
- metric_method
- published WER/RTFx
- metric_kind
- MLS WER (WER)
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- hf-audio/multilingual_evals/multilingual_nl.csv
- published_at
- 2026-10-21T14:20:31Z
- source_revision
- 943867e1b478153a2161b0522c130917d0d96b01a780660e00252b573bc2cf13
- metric_population
- 36
- benchmark_evaluation
- true
- source model id
- openai/whisper-large-v3-turbo
Original result ↗Published prices
1–2 / 2
$0.0005
- Inference provider
- cloudflareWorkersAI
- Platform
- Cloudflare Workers AI
- Unit
- second
- Currency
- USD
- Billing label
- per audio minute
$0.000003
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- second
- Currency
- USD
- Billing conditions
- direction
- input
- Billing label
- Input audio second
Provider specifications & access
1–7 / 7
- source model id
- azure-huggingface/openai--whisper-large-v3-turbo@1
- hosting
- foundry-managed-compute
- license
- MIT
- source model id
- azure-huggingface/openai--whisper-large-v3-turbo@2
- hosting
- foundry-managed-compute
- license
- MIT
- source model id
- azure-huggingface/openai--whisper-large-v3-turbo@3
- hosting
- foundry-managed-compute
- license
- MIT
- source model id
- @cf/openai/whisper-large-v3-turbo
- hosting
- cloudflare-hosted
- source model id
- HuggingFace/openai-whisper-large-v3-turbo@4
- hosting
- foundry-managed-compute
- license
- mit
- source model id
- publishers/openai/models/whisper-large@whisper-large-v3-turbo
- hosting
- vertex-self-deployed
- source model id
- whisper-large-v3-turbo
- hosting
- gateway
Safety assessments
1–1 / 1
35 / 100
- source id
- stanfordFMTI
- canonical model id
- openai/whisper-large-v3-turbo
- taxonomy
- transparency
- hazard category
- transparency
- hazard name
- Organization transparency
- policy area
- OpenAI
- assessment type
- organization-level disclosure
- metric
- disclosure_score
- result label
- 35 / 100
- sample size
- 100
- updated at
- 2026-11-09T18:08:05.227Z
Hugging Face model card
1–1 / 1
- downloads
- 4764975
- likes
- 3551
- pipeline tag
- automatic-speech-recognition
- library name
- transformers
- License
- mit
Explore more models