Muse Voice Transcribe

Competitive latency and streaming transcription accuracy with live attribution for 20+ speakers. Build with a single model at $0.18/hour.

Start building

Documentation

Meet Muse Voice Transcribe

Competitive transcription accuracy

Leading streaming word error rate, and it holds that accuracy on your vocabulary through contextual and keyword biasing, with no fine-tuning.

Live speaker and turn awareness

Speaker attribution for 20+ speakers and end-of-speech detection happen inside the recognition model, not in a batch pass at the end of the audio stream.

Production pricing

Ship with leading transcription accuracy and streaming capabilities without compromising on costs.