Updated daily at 05:00 UTC
Models
Speech-to-text models
69 models listed.
Models
- Whisper large-v3OpenAI · 6 Nov 2023 · — context—in / 1M
- MMS-1B-allMeta · May 2023 · — context—in / 1M
- Whisper large-v2OpenAI · 5 Dec 2022 · — context—in / 1M
- Whisper (large-v1 and smaller sizes)OpenAI · 21 Sep 2022 · — context—in / 1M
- Bulbul v3Sarvam AI · — · — context—in / 1M
- Chirp 2Google · — · — context—in / 1M
- Deepgram BaseDeepgram · — · — context—in / 1M
- Deepgram EnhancedDeepgram · — · — context—in / 1M
- Deepgram NovaDeepgram · — · — context—in / 1M
- Deepgram Nova-2Deepgram · — · — context—in / 1M
- Deepgram Nova-3 MedicalDeepgram · — · — context—in / 1M
- Deepgram Nova-3 PharmaDeepgram · — · — context—in / 1M
- GPT-4o Transcribe DiarizeOpenAI · — · 16K context$2.50in / 1M
- Muse Voice Transcribe 1.0Meta · — · — context—in / 1M
- Saaras v3Sarvam AI · — · — context—in / 1M
- SaarikaSarvam AI · — · — context—in / 1M
- Scribe v2 (and v2 Realtime)ElevenLabs · — · — context—in / 1M
- Step ASRStepFun · — · — context—in / 1M
- StepAudio 3 ASRStepFun · — · — context—in / 1M