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 · Hindi RTFxLanguagesPriceReleased
OmniASR CTC 300M v2Meta
970.8
—
OmniASR CTC 1B v2Meta
656.5
—
Nemotron 3.5 ASR Streaming 0.6BNVIDIAOpen
517.4
en, es, fr +31May 2026
OmniASR CTC 3B v2Meta
438.9
—
Whisper Large v3 TurboOpenAIOpen
251.7
en, es, fr +86$0.001 / minuteOct 2024
OmniASR CTC 7B v2Meta
251.3
—
ASraVaani 1.0ARTPARK-IIScOpen
184.1
en, hi, kn +10Feb 2026
Voxtral Mini 3B 2507MistralOpen
98.2
en, es, fr +5$0.001 / minuteJul 2025
Whisper Large v3OpenAIOpen
89.6
en, es, fr +86$0.004 / minuteSep 2022
Gemma 4 E4B ItGoogleOpen
82.3
—$0.02 / 1M billed tokensMar 2026
Qwen 3 ASR 1.7B HfAlibaba (Qwen)Open
79.4
en, es, fr +25Jun 2026
Qwen 3 ASR 0.6B HfAlibaba (Qwen)Open
78.5
en, es, fr +25Jun 2026
bShrutam 2bharatgenaiOpen
65.2
hi, mr, ta +8Feb 2026
VibeVoice ASR HFMicrosoftOpen
58.3
en, es, fr +45Mar 2026
Voxtral Small 24B 2507MistralOpen
53
en, es, fr +5$0.003 / minuteJul 2025
Voxtral Mini 4B Realtime 2602MistralOpen
33.8
en, es, fr +10Jan 2026
OmniASR LLM 300M v2Meta
29.8
—
OmniASR LLM 1B v2Meta
29.4
—
OmniASR LLM 3B v2Meta
28.2
—
OmniASR LLM 7B v2Meta
27.3
—
aIndic Conformer 600M Multilingualai4bharat
7.7
—Mar 2025