Audience
Developers and AI researchers seeking to build real-time voice applications that transcribe multilingual speech, distinguish speakers, and detect conversational turns
About Muse Voice Transcribe
Muse Voice Transcribe is Meta’s first real-time audio perception model, delivering streaming automatic speech recognition (ASR), diarization, and endpointing in real time. An autoregressive multimodal model from the Muse Spark family, it processes audio in 80 ms chunks and decides dynamically whether to continue listening or emit text. Its adaptive delay changes the amount of audio context used for each word based on difficulty, balancing transcription accuracy with latency. The model is trained on more than 70 languages, with 25 extensively verified at launch, and natively supports arbitrary code-switching both within and between sentences. Language, keyword, and context biasing can further improve recognition accuracy for specific names, places, contacts, or terminology. Streaming diarization identifies speaker changes and distinguishes more than 20 speakers, while endpointing detects when speech begins and when a user finishes speaking.
Pricing
Integrations
Company Information
Videos and Screen Captures
