HomeSpeech-to-text

Open-source speech-to-text models

22 speech-to-text models from 13 publishers publish their weights, so you can run them yourself. Licences differ, so check commercial use on each model.

The cheapest published USD price is MiMo-V2.5-ASR from Xiaomi MiMo at $0.07 per hour; 3 of 22 have a comparable price.

Of these, 3 stream over WebSocket or WebRTC and 1 has an announced shutdown date.

Prices are normalized: USD per hour of audio, cheapest first. Tick models to compare them side by side, or refine these filters.

22 matches

Speech-to-text and realtime $ per hour of audio, log scale 236 priced, 280 without a USD price

Speech-to-text and realtime: 236 models with a published USD price per hour of audio, from $0.05 to $20 and beyond, shown on a log scale.

other models matches your filtersAll models by price

Compare Model Provider Type Langs Features Price ↑ Status
mimo-v2.5-asrMiMo-V2.5-ASRXiaomi MiMo, STT Xiaomi MiMo STT 2 2/11 $0.07 per hour Default
horizon-universalHorizon UniversalShunya Labs, STT Shunya Labs STT Many 7/11 $0.23 per hour
voxtral-mini-transcribe-realtime-2602Voxtral Mini Transcribe Realtime (26.02)Mistral AI, STT, ends 2027-04-30 Mistral AI STT 13 0/11 $0.36 per hour Ends 2027-04-30
ai4bharat/indic-conformer-600m-multilingualindic-conformer-600m-multilingualAI4Bharat, STT AI4Bharat STT – 0/11 –
cohere-transcribe-03-2026Cohere TranscribeCohere, STT Cohere STT 14 0/11 – Default
cohere-transcribe-arabic-07-2026Cohere Transcribe ArabicCohere, STT Cohere STT 2 0/11 –
FunAudioLLM/Fun-ASR-Nano-2512Fun-ASR-Nano-2512FunAudioLLM (Alibaba Tongyi), STT FunAudioLLM (Alibaba Tongyi) STT 12 0/11 –
FunAudioLLM/SenseVoiceSmallSenseVoiceSmallFunAudioLLM (Alibaba Tongyi), STT FunAudioLLM (Alibaba Tongyi) STT 5 0/11 –
chinda-asr-realtime-v1OpenThai ASR RealtimeiApp Technology, STT iApp Technology STT 1 0/11 –
microsoft/Phi-4-multimodal-instructPhi-4-multimodal-instructMicrosoft (open weights), STT Microsoft (open weights) STT 23 0/11 –
microsoft/VibeVoice-ASRVibeVoice-ASRMicrosoft (open weights), STT Microsoft (open weights) STT 51 0/11 –
microsoft/VibeVoice-ASR-BitNetVibeVoice-ASR-BitNetMicrosoft (open weights), STT Microsoft (open weights) STT 7 0/11 –
microsoft/VibeVoice-ASR-Streaming-7BVibeVoice-ASR-Streaming-7BMicrosoft (open weights), STT Microsoft (open weights) STT 10 0/11 –
nvidia/nemotron-asr-streamingNemotron ASR StreamingNVIDIA, STT NVIDIA STT 36 4/11 –
nvidia/nemotron-transcribeNemotron 3.5 TranscribeNVIDIA, STT NVIDIA STT 40 3/11 –
nvidia/parakeet-tdt-0_6bParakeet TDT 0.6B v3NVIDIA, STT NVIDIA STT 25 3/11 –
nvidia/parakeet-tdt-0_6b-v2Parakeet TDT 0.6B v2NVIDIA, STT NVIDIA STT 1 2/11 –
rumble-2-flashRumble-2-FlashReson8, STT Reson8 STT 45 0/11 €0.0114 per hour
ai-sage/GigaAM-MultilingualGigaAM-MultilingualSber SaluteSpeech, STT Sber SaluteSpeech STT 5 0/11 –
ai-sage/GigaAM-v3GigaAM-v3Sber SaluteSpeech, STT Sber SaluteSpeech STT 2 0/11 –
Sunbird/faster-whisper-51-african-languagesSunbird ASR (Whisper large-v3, 51 African languages)Sunbird AI, STT Sunbird AI STT 51 0/11 – Default
t-tech/T-oneT-oneT-Bank VoiceKit, STT T-Bank VoiceKit STT 1 0/11 –

Speech-to-text by feature

Speech-to-text by language

Other model types

Esc

↑↓ move↵ open