S1 Voice
S1-Voice is Superwhisper’s cloud speech-recognition model for high-accuracy, low-latency transcription across 100+ languages inside the Superwhisper dictation workflow.
- Type
- Multimodal
- Weights
- Closed
More from Superwhisper
4
About Superwhisper
1
Superwhisper is an AI-native voice-to-text platform for macOS, Windows, and iOS. It converts speech into polished text inside other applications using local or cloud AI models, with support for more than 100 languages, meeting transcription, and customizable transcription modes.