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 · RTFxLanguagesPriceReleased
Granite Speech 5.0 470M TurboctcIBMOpen
21,134.3
enAug 2026
Granite Speech 5.0 470M Turboctc NcIBMOpen
20,801.3
enAug 2026
sZipformer-cr-ctc-transducer-XL-290M (fast-gpu-asr, transducer_modified_beam_search)soundsgoodaiOpen
19,289.7
enJul 2026
aNiagara 9M Batch.enabr-aiOpen
7,217
enSep 2026
Parakeet TDT 0.6B V3, TogetheraiNVIDIAOpen
6,227.7
en, es, fr +21$0.002 / minuteAug 2025
Parakeet TDT 0.6B V2, NVIDIANVIDIAOpen
6,148.3
enMay 2025
Parakeet Ctc 1.1BNVIDIAOpen
5,137.4
enDec 2023
aNiagara 38M Batch.enabr-aiOpen
4,561.4
enFeb 2026
aNiagara 19M Batch.enabr-aiOpen
4,348.4
enNov 2025
Granite Speech 4.1 2B NarIBMOpen
2,112.6
en, es, fr +2Mar 2026
FPhonon 2FermionResearchOpen
1,976.5
enSep 2026
aNiagara 84M Batch.enabr-aiOpen
1,940.8
enSep 2026
Canary 1B v2NVIDIAOpen
1,853.7
en, es, fr +21Aug 2025
Nemotron 3.5 ASR Streaming 0.6BNVIDIAOpen
1,348.4
en, es, fr +31May 2026
TThewhisper Large v3 TurboTheStageAIOpen
1,183.9
en, es, fr +24Oct 2025
Nemotron Speech Streaming En 0.6BNVIDIAOpen
1,114.1
—Dec 2025
CCohere Transcribe 03 2026CohereLabsOpen
923.7
en, es, fr +10Mar 2026
dDistil Large v3.5distil-whisperOpen
898.2
enDec 2024
Canary Qwen 2.5B, NVIDIANVIDIAOpen
881.7
en$0.001 / minuteJul 2025
Qwen 3 ASR 1.7B HfAlibaba (Qwen)Open
835.6
en, es, fr +25Jun 2026
Whisper Large v3 TurboOpenAIOpen
810.5
en, es, fr +86$0.001 / minuteOct 2024
eOwsm Ctc v4 1BespnetOpen
783.3
—Jan 2025
Qwen 3 ASR 0.6B HfAlibaba (Qwen)Open
749.5
en, es, fr +25Jun 2026
EAudio8 ASR 0.1BEdge0Open
725.8
en, fr, de +3Jul 2026
EARK ASR 0.6BEdge0Open
673
en, es, fr +16May 2026
Granite 4.0 1B SpeechIBMOpen
667
en, es, fr +3Feb 2026
Granite Speech 4.1 2BIBMOpen
546.8
en, es, fr +3Apr 2026
OmniASR CTC 7B v2Meta
522.3
—
Granite Speech 3.3 2BIBMOpen
509.4
en, es, fr +2Apr 2025
FFun ASR Nano 2512 HfFunAudioLLMOpen
506.4
en, zh, jaMay 2026
EARK ASR 3BEdge0Open
480.1
en, es, fr +16Jun 2026
Whisper Large v3OpenAIOpen
470.7
en, es, fr +86$0.004 / minuteSep 2022
OMOSS Transcribe DiarizeOpenMOSS-TeamOpen
387.5
en, zhMay 2026
Granite Speech 3.3 8BIBMOpen
262.8
en, es, fr +2Apr 2025
VibeVoice ASR HFMicrosoftOpen
217.9
en, es, fr +45Mar 2026
Gemma 4 E2B ItGoogleOpen
190.8
—Mar 2026
Voxtral Mini 3B 2507MistralOpen
179.8
en, es, fr +5$0.001 / minuteJul 2025
Phi 4 Multimodal InstructMicrosoftOpen
162.5
en, es, fr +20$0.05 / 1M billed tokensFeb 2025
Gemma 4 E4B ItGoogleOpen
160.7
—$0.02 / 1M billed tokensMar 2026
OmniASR LLM 7B v2Meta
129.8
—
BHiggs Audio v3 SttBoson AIOpen
109.7
enMar 2026
Gemma 4 12B ItGoogleOpen
106.1
—May 2026
Voxtral Mini 4B Realtime 2602MistralOpen
103.5
en, es, fr +10Jan 2026
Voxtral Small 24B 2507MistralOpen
101.5
en, es, fr +5$0.003 / minuteJul 2025
HHojo ASR v1HojoAIOpen
73.4
en, zhMay 2026