Team · Intermediate
Process audio recordings into speaker-labeled transcripts
Turn multi-speaker audio files into timestamped transcripts with speaker segmentation and clean punctuation
- When you askReceive audio recording path
- ThenExecute transcription and diarization
- ResultRequest approval to post final
Process raw audio recordings through automated speech recognition, voice activity detection, and speaker diarization pipelines. The bot turns audio inputs into readable, timestamped dialogue records organized by speaker, saving teams time when documenting calls, interviews, or operational discussions.
Prompt to start with
BotBentoRecommended
When an audio file or URL is provided, run the local speech processing pipeline via terminal to detect speech segments and separate speakers. Format the resulting output with timestamps and speaker identifiers into a clean document in notes. Review the text for formatting errors. Do not share or post the finalized transcript to Slack or message channels without explicit user approval.