What problem does it solve? Converting spoken audio into accurate written text manually is slow and error-prone, especially for long recordings, multi-speaker meetings, or content in multiple languages. This Skill provides programmatic access to ElevenLabs Scribe v2 for batch and real-time transcription. ## Core Features & Use Cases - Batch Transcription: Convert audio and video files (MP3, WAV, MP4, and more) to text across 90+ languages with word-level timestamps. - Speaker Diarization: Identify who said what in meetings and interviews, with support for up to 32 speakers. - Real-Time Streaming: Transcribe live microphone input or audio streams with ~150ms latency using partial and committed transcripts with VAD-based commit strategies. - Use Case: Transcribe a recorded team meeting with speaker labels and keyterm prompting for company-specific jargon, then export the result as SRT subtitles. ## Quick Start Transcribe the attached audio file 'meeting.mp3' to text with speaker diarization and word-level timestamps using the ElevenLabs speech-to-text skill.
