Tag
2 articles
Microsoft AI has released MAI-Transcribe-2-Streaming, a real-time speech-to-text model that ranks #1 on the Artificial Analysis AA-WER Streaming benchmark. It delivers 2.5% WER with sub-second processing times across 60 languages.
Meta's new real-time audio model, Muse Voice Transcribe, promises to revolutionize AI assistants by enabling accurate, low-latency speech processing and speaker identification.