Best for Speech & Voice

All models2292Chat & Knowledge558Coding381Agents & Tool Use541Writing & Language360Vision & Documents395Image Generation & Editing183Video Generation148Speech & Voice358Embeddings & Retrieval671Decision models118Music & Sound29
Text to speech136Speech to text151Realtime55Translation8Voice changers4
ModelOpen ASR · German RTFxLanguagesPriceReleased
Parakeet TDT 0.6B V3, TogetheraiNVIDIAOpen
3,362.9
en, es, fr +21$0.002 / minuteAug 2025
Granite Speech 4.1 2B NarIBMOpen
1,402.4
en, es, fr +2Mar 2026
Canary 1B v2NVIDIAOpen
1,307.8
en, es, fr +21Aug 2025
Nemotron 3.5 ASR Streaming 0.6BNVIDIAOpen
1,110
en, es, fr +31May 2026
OmniASR CTC 300M v2Meta
1,011.4
—
TThewhisper Large v3 TurboTheStageAIOpen
960.4
en, es, fr +24Oct 2025
OmniASR CTC 1B v2Meta
762.4
—
CCohere Transcribe 03 2026CohereLabsOpen
606.9
en, es, fr +10Mar 2026
OmniASR CTC 3B v2Meta
526.6
—
Qwen 3 ASR 0.6B HfAlibaba (Qwen)Open
384.3
en, es, fr +25Jun 2026
Qwen 3 ASR 1.7B HfAlibaba (Qwen)Open
368.6
en, es, fr +25Jun 2026
Whisper Large v3 TurboOpenAIOpen
338.3
en, es, fr +86$0.001 / minuteOct 2024
Whisper Large v3OpenAIOpen
327.6
en, es, fr +86$0.004 / minuteSep 2022
OmniASR CTC 7B v2Meta
310.8
—
OMOSS Transcribe DiarizeOpenMOSS-TeamOpen
243.3
en, zhMay 2026
Voxtral Mini 3B 2507MistralOpen
149.7
en, es, fr +5$0.001 / minuteJul 2025
Gemma 4 E4B ItGoogleOpen
135.8
—$0.02 / 1M billed tokensMar 2026
Phi 4 Multimodal InstructMicrosoftOpen
122.7
en, es, fr +20$0.05 / 1M billed tokensFeb 2025
VibeVoice ASR HFMicrosoftOpen
113.7
en, es, fr +45Mar 2026
Voxtral Small 24B 2507MistralOpen
83
en, es, fr +5$0.003 / minuteJul 2025
OmniASR LLM 300M v2Meta
47.8
—
OmniASR LLM 1B v2Meta
47.1
—
HHojo ASR Multi v1HojoAIOpen
46.8
es, fr, de +2Aug 2026
OmniASR LLM 3B v2Meta
45.3
—
OmniASR LLM 7B v2Meta
42.5
—
Voxtral Mini 4B Realtime 2602MistralOpen
42.1
en, es, fr +10Jan 2026