Meta has launched Muse Voice Transcribe, its first real-time audio perception model, with native support for five major Indian languages and streaming transcription features. Developed by Meta Superintelligence Labs, the model provides real-time speech-to-text transcription, speaker separation and multilingual code-switching without a separate post-processing step. It has been trained on more than 70 languages, with 25 languages validated at launch. Meta said the model ranked first on the Artificial Analysis streaming speech-to-text leaderboard as of Sept. 1, 2026. It is available through the Meta Model API and is already used for dictation in Meta AI for Mac and Muse Code. Key features include automatic speech recognition, speaker diarization for more than 20 speakers in recordings lasting more than an hour, endpoint detection and seamless language switching. Accuracy can be improved with language, keyword and contextual guidance. The model uses an “adaptive delay” system, powered by reinforcement learning, that balances word error rates against transcription delay. Meta described Muse Voice Transcribe as an autoregressive multimodal model from its Muse Spark family, processing audio in 80-millisecond segments, each converted into a single soft token.