NVIDIA: Parakeet TDT 0.6B v3
Parakeet TDT 0.6B v3 is NVIDIA's 600M-parameter multilingual speech-to-text model built on the FastConformer-TDT architecture. Trained on the Granary dataset (670,000+ hours of audio), it supports au…
nvidia/parakeet-tdt-0.6b-v3
Parakeet TDT 0.6B v3 is NVIDIA's 600M-parameter multilingual speech-to-text model built on the FastConformer-TDT architecture. Trained on the Granary dataset (670,000+ hours of audio), it supports automatic language detection across all official EU languages and achieves a 6.34% average word error rate on the HuggingFace Open ASR Leaderboard. Returns transcribed text with punctuation and segment timestamps.
Specifications & capabilities
- Input
- audio
- Output
- transcription
- Context window · tokens
- 0
- Published model ID
- parakeet-tdt-0.6b-v3
- Capabilities
- audioInput
Description source ↗Evaluations
1–20 / 114
1,719.32
- source id
- openASR
- leaderboard name
- RTFx
- dimension
- runtime
- metric
- RTFx
- rank
- 1
- 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
- nvidia/parakeet-tdt-0.6b-v3
Original result ↗3,786.16
- source id
- openASR
- leaderboard name
- RTFx
- dimension
- runtime
- metric
- RTFx
- rank
- 2
- 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
- nvidia/parakeet-tdt-0.6b-v3
Original result ↗3,618.38
- source id
- openASR
- leaderboard name
- RTFx
- dimension
- runtime
- metric
- RTFx
- rank
- 2
- 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
- nvidia/parakeet-tdt-0.6b-v3
Original result ↗3,427.19
- source id
- openASR
- leaderboard name
- RTFx
- dimension
- runtime
- metric
- RTFx
- rank
- 2
- 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
- nvidia/parakeet-tdt-0.6b-v3
Original result ↗3,362.94
- source id
- openASR
- leaderboard name
- RTFx
- dimension
- runtime
- metric
- RTFx
- rank
- 2
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- hf-audio/multilingual_evals/multilingual_de.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_de.csv
- published_at
- 2026-10-21T14:20:31Z
- source_revision
- 943867e1b478153a2161b0522c130917d0d96b01a780660e00252b573bc2cf13
- metric_population
- 27
- benchmark_evaluation
- true
- source model id
- nvidia/parakeet-tdt-0.6b-v3
Original result ↗3,256.94
- source id
- openASR
- leaderboard name
- 🇵🇹 Portuguese · RTFx
- dimension
- runtime
- metric
- 🇵🇹 Portuguese · RTFx
- rank
- 2
- 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
- nvidia/parakeet-tdt-0.6b-v3 🤗
Original result ↗3,256.94
- source id
- openASR
- leaderboard name
- RTFx
- dimension
- runtime
- metric
- RTFx
- rank
- 2
- 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
- nvidia/parakeet-tdt-0.6b-v3
Original result ↗2,782.68
- source id
- openASR
- leaderboard name
- RTFx
- dimension
- runtime
- metric
- RTFx
- rank
- 2
- 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
- nvidia/parakeet-tdt-0.6b-v3
Original result ↗1,002.91
- source id
- openASR
- leaderboard name
- RTFx
- dimension
- runtime
- metric
- RTFx
- rank
- 2
- 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
- nvidia/parakeet-tdt-0.6b-v3
Original result ↗3,786.16
- source id
- openASR
- leaderboard name
- 🇪🇸 Spanish · RTFx
- dimension
- runtime
- metric
- 🇪🇸 Spanish · RTFx
- rank
- 3
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- view
- multilingual/spanish
- suite
- OpenASR official public table
- metric_method
- publisher WER/RTFx for selected public view
- space_revision
- 3b5317f4e49b6cb40502b95065b29fbfe08284ce
- publisher_version
- 13-11-2026
- metric_kind
- 🇪🇸 Spanish · RTFx
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- public/multilingual/spanish.json
- published_at
- 2026-11-13T11:42:34Z
- source_revision
- 8f2cc9c9f3b01b8670c8640efc67f24a3ea076c2bf5e90e7c674a1a829d69bd7
- metric_population
- 33
- benchmark_evaluation
- true
- source model id
- nvidia/parakeet-tdt-0.6b-v3 🤗
Original result ↗3,618.38
- source id
- openASR
- leaderboard name
- 🇫🇷 French · RTFx
- dimension
- runtime
- metric
- 🇫🇷 French · RTFx
- rank
- 3
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- view
- multilingual/french
- suite
- OpenASR official public table
- metric_method
- publisher WER/RTFx for selected public view
- space_revision
- 3b5317f4e49b6cb40502b95065b29fbfe08284ce
- publisher_version
- 13-11-2026
- metric_kind
- 🇫🇷 French · RTFx
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- public/multilingual/french.json
- published_at
- 2026-11-13T11:42:34Z
- source_revision
- 8f2cc9c9f3b01b8670c8640efc67f24a3ea076c2bf5e90e7c674a1a829d69bd7
- metric_population
- 33
- benchmark_evaluation
- true
- source model id
- nvidia/parakeet-tdt-0.6b-v3 🤗
Original result ↗3,427.19
- source id
- openASR
- leaderboard name
- 🇮🇹 Italian · RTFx
- dimension
- runtime
- metric
- 🇮🇹 Italian · RTFx
- rank
- 3
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- view
- multilingual/italian
- suite
- OpenASR official public table
- metric_method
- publisher WER/RTFx for selected public view
- space_revision
- 3b5317f4e49b6cb40502b95065b29fbfe08284ce
- publisher_version
- 13-11-2026
- metric_kind
- 🇮🇹 Italian · RTFx
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- public/multilingual/italian.json
- published_at
- 2026-11-13T11:42:34Z
- source_revision
- 8f2cc9c9f3b01b8670c8640efc67f24a3ea076c2bf5e90e7c674a1a829d69bd7
- metric_population
- 32
- benchmark_evaluation
- true
- source model id
- nvidia/parakeet-tdt-0.6b-v3 🤗
Original result ↗3,362.94
- source id
- openASR
- leaderboard name
- 🇩🇪 German · RTFx
- dimension
- runtime
- metric
- 🇩🇪 German · RTFx
- rank
- 3
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- view
- multilingual/german
- suite
- OpenASR official public table
- metric_method
- publisher WER/RTFx for selected public view
- space_revision
- 3b5317f4e49b6cb40502b95065b29fbfe08284ce
- publisher_version
- 13-11-2026
- metric_kind
- 🇩🇪 German · RTFx
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- public/multilingual/german.json
- published_at
- 2026-11-13T11:42:34Z
- source_revision
- 8f2cc9c9f3b01b8670c8640efc67f24a3ea076c2bf5e90e7c674a1a829d69bd7
- metric_population
- 33
- benchmark_evaluation
- true
- source model id
- nvidia/parakeet-tdt-0.6b-v3 🤗
Original result ↗2,782.68
- source id
- openASR
- leaderboard name
- 🇳🇱 Dutch · RTFx
- dimension
- runtime
- metric
- 🇳🇱 Dutch · RTFx
- rank
- 3
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- view
- multilingual/dutch
- suite
- OpenASR official public table
- metric_method
- publisher WER/RTFx for selected public view
- space_revision
- 3b5317f4e49b6cb40502b95065b29fbfe08284ce
- publisher_version
- 13-11-2026
- metric_kind
- 🇳🇱 Dutch · RTFx
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- public/multilingual/dutch.json
- published_at
- 2026-11-13T11:42:34Z
- source_revision
- 8f2cc9c9f3b01b8670c8640efc67f24a3ea076c2bf5e90e7c674a1a829d69bd7
- metric_population
- 30
- benchmark_evaluation
- true
- source model id
- nvidia/parakeet-tdt-0.6b-v3 🤗
Original result ↗1,419.11
- source id
- openASR
- leaderboard name
- Long-form · RTFx
- dimension
- runtime
- metric
- Long-form · RTFx
- rank
- 3
- 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
- nvidia/parakeet-tdt-0.6b-v3 🤗
Original result ↗7,408.562
- source id
- openASR
- leaderboard name
- Voxpopuli-AA-Cleaned RTFx
- dimension
- runtime
- metric
- Voxpopuli-AA-Cleaned RTFx
- rank
- 7
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- hf-audio/open-asr-leaderboard-results/english_short_latest.csv
- metric_method
- published WER/RTFx
- metric_kind
- Voxpopuli-AA-Cleaned RTFx
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- hf-audio/open-asr-leaderboard-results/english_short_latest.csv
- published_at
- 2026-10-21T14:20:31Z
- source_revision
- 943867e1b478153a2161b0522c130917d0d96b01a780660e00252b573bc2cf13
- metric_population
- 49
- benchmark_evaluation
- true
- source model id
- nvidia/parakeet-tdt-0.6b-v3
Original result ↗14.47%
- source id
- openASR
- leaderboard name
- Long-form · CORAAL (WER)
- dimension
- speech
- metric
- Long-form · CORAAL (WER)
- rank
- 7
- 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
- nvidia/parakeet-tdt-0.6b-v3 🤗
Original result ↗7,343.977
- source id
- openASR
- leaderboard name
- SPGISpeech RTFx
- dimension
- runtime
- metric
- SPGISpeech RTFx
- rank
- 8
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- hf-audio/open-asr-leaderboard-results/english_short_latest.csv
- metric_method
- published WER/RTFx
- metric_kind
- SPGISpeech RTFx
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- hf-audio/open-asr-leaderboard-results/english_short_latest.csv
- published_at
- 2026-10-21T14:20:31Z
- source_revision
- 943867e1b478153a2161b0522c130917d0d96b01a780660e00252b573bc2cf13
- metric_population
- 49
- benchmark_evaluation
- true
- source model id
- nvidia/parakeet-tdt-0.6b-v3
Original result ↗6,227.73
- source id
- openASR
- leaderboard name
- RTFx
- dimension
- runtime
- metric
- RTFx
- rank
- 8
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- hf-audio/open-asr-leaderboard-results/english_short_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/open-asr-leaderboard-results/english_short_latest.csv
- published_at
- 2026-10-21T14:20:31Z
- source_revision
- 943867e1b478153a2161b0522c130917d0d96b01a780660e00252b573bc2cf13
- metric_population
- 49
- benchmark_evaluation
- true
- source model id
- nvidia/parakeet-tdt-0.6b-v3
Original result ↗4,353.569
- source id
- openASR
- leaderboard name
- LS Other RTFx
- dimension
- runtime
- metric
- LS Other RTFx
- rank
- 8
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- hf-audio/open-asr-leaderboard-results/english_short_latest.csv
- metric_method
- published WER/RTFx
- metric_kind
- LS Other RTFx
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- hf-audio/open-asr-leaderboard-results/english_short_latest.csv
- published_at
- 2026-10-21T14:20:31Z
- source_revision
- 943867e1b478153a2161b0522c130917d0d96b01a780660e00252b573bc2cf13
- metric_population
- 49
- benchmark_evaluation
- true
- source model id
- nvidia/parakeet-tdt-0.6b-v3
Original result ↗Published prices
1–1 / 1
$0.000017
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- second
- Currency
- USD
- Billing conditions
- direction
- input
- Billing label
- Input audio second
Provider specifications & access
1–2 / 2
- source model id
- HuggingFace/nvidia-parakeet-tdt-0.6b-v3@1
- hosting
- foundry-managed-compute
- license
- cc-by-4.0
- source model id
- HuggingFace/nvidia-parakeet-tdt-0.6b-v3@2
- hosting
- foundry-managed-compute
- license
- cc-by-4.0
Explore more models