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 · Portuguese RTFxLanguagesPriceReleased
Parakeet TDT 0.6B V3, TogetheraiNVIDIAOpen
3,256.9
en, es, fr +21$0.002 / minuteAug 2025
TThewhisper Large v3 TurboTheStageAIOpen
1,582.7
en, es, fr +24Oct 2025
Granite Speech 4.1 2B NarIBMOpen
1,432.1
en, es, fr +2Mar 2026
Canary 1B v2NVIDIAOpen
1,367
en, es, fr +21Aug 2025
Whisper Large v3 TurboOpenAIOpen
974.1
en, es, fr +86$0.001 / minuteOct 2024
OmniASR CTC 300M v2Meta
969.9
—
Nemotron 3.5 ASR Streaming 0.6BNVIDIAOpen
869.3
en, es, fr +31May 2026
OmniASR CTC 1B v2Meta
713.2
—
CCohere Transcribe 03 2026CohereLabsOpen
572
en, es, fr +10Mar 2026
OmniASR CTC 3B v2Meta
485.1
—
Whisper Large v3OpenAIOpen
351.9
en, es, fr +86$0.001 / minuteSep 2022
Qwen 3 ASR 1.7B HfAlibaba (Qwen)Open
337.3
en, es, fr +25Jun 2026
Qwen 3 ASR 0.6B HfAlibaba (Qwen)Open
319.5
en, es, fr +25Jun 2026
OmniASR CTC 7B v2Meta
275.6
—
Voxtral Mini 3B 2507MistralOpen
194.1
en, es, fr +5$0.001 / minuteJul 2025
OMOSS Transcribe DiarizeOpenMOSS-TeamOpen
154.7
en, zhMay 2026
Gemma 4 E4B ItGoogleOpen
130.8
—$0.02 / 1M billed tokensMar 2026
VibeVoice ASR HFMicrosoftOpen
123.3
en, es, fr +45Mar 2026
Voxtral Small 24B 2507MistralOpen
122.8
en, es, fr +5$0.003 / minuteJul 2025
Phi 4 Multimodal InstructMicrosoftOpen
118.5
en, es, fr +20$0.05 / 1M billed tokensFeb 2025
Voxtral Mini 4B Realtime 2602MistralOpen
39.8
en, es, fr +10Jan 2026
OmniASR LLM 300M v2Meta
39.2
—
OmniASR LLM 1B v2Meta
38.3
—
OmniASR LLM 3B v2Meta
37.4
—
HHojo ASR Multi v1HojoAIOpen
36.8
es, fr, de +2Aug 2026
OmniASR LLM 7B v2Meta
35.1
—