Best for Speech & Voice

All models2314Chat & Knowledge563Coding383Agents & Tool Use543Writing & Language361Vision & Documents397Image Generation & Editing184Video Generation148Speech & Voice358Embeddings & Retrieval688Decision models118Music & Sound29
Text to speech136Speech to text151Realtime55Translation8Voice changers4
ModelOpen ASR · Italian RTFxLanguagesPer audio minutePriceReleased
Parakeet TDT 0.6B V3, TogetheraiNVIDIAOpen
3,427.2
en, es, fr +21$0.002 / min$0.002 / minuteAug 2025
Canary 1B v2NVIDIAOpen
1,361.6
en, es, fr +21—Aug 2025
Nemotron 3.5 ASR Streaming 0.6BNVIDIAOpen
1,205.2
en, es, fr +31—May 2026
TThewhisper Large v3 TurboTheStageAIOpen
1,116.7
en, es, fr +24—Oct 2025
OmniASR CTC 300M v2Meta
1,041.2
——
OmniASR CTC 1B v2Meta
815.1
——
CCohere Transcribe 03 2026CohereLabsOpen
687.5
en, es, fr +10—Mar 2026
OmniASR CTC 3B v2Meta
558.1
——
Whisper Large v3 TurboOpenAIOpen
423
en, es, fr +86$0.001 / min$0.001 / minuteOct 2024
Qwen 3 ASR 1.7B HfAlibaba (Qwen)Open
389.9
en, es, fr +25—Jun 2026
Qwen 3 ASR 0.6B HfAlibaba (Qwen)Open
384.7
en, es, fr +25—Jun 2026
Whisper Large v3OpenAIOpen
368.9
en, es, fr +86$0.004 / min$0.001 / minuteSep 2022
OmniASR CTC 7B v2Meta
330.3
——
OMOSS Transcribe DiarizeOpenMOSS-TeamOpen
270.7
en, zh—May 2026
Voxtral Mini 3B 2507MistralOpen
169.7
en, es, fr +5$0.001 / min$0.001 / minuteJul 2025
Gemma 4 E4B ItGoogleOpen
141.1
——$0.02 / 1M billed tokensMar 2026
VibeVoice ASR HFMicrosoftOpen
126
en, es, fr +45—Mar 2026
Phi 4 Multimodal InstructMicrosoftOpen
122.6
en, es, fr +20—$0.05 / 1M billed tokensFeb 2025
Voxtral Small 24B 2507MistralOpen
97.6
en, es, fr +5$0.003 / min$0.003 / minuteJul 2025
OmniASR LLM 300M v2Meta
52.8
——
OmniASR LLM 1B v2Meta
51.8
——
OmniASR LLM 3B v2Meta
51
——
Voxtral Mini 4B Realtime 2602MistralOpen
49.2
en, es, fr +10—Jan 2026
HHojo ASR Multi v1HojoAIOpen
48.2
es, fr, de +2—Aug 2026
OmniASR LLM 7B v2Meta
47.6
——