For the complete documentation index, see llms.txt. This page is also available as Markdown.

Offline Meeting Transcription

Offline mode lets you upload pre-recorded audio files. The system performs high-accuracy transcription and speaker identification, generating a transcript with timeline markers.

Supported Audio Formats

Format
Extension

MP3

.mp3

MP4

.mp4

M4A

.m4a

AAC

.aac

WAV

.wav

Upload Audio

  1. Go to the "Meeting Records" page

  2. Select upload audio

  3. Choose a local audio file (supports mp3, mp4, m4a, aac, wav)

  4. The system begins background processing

After uploading, the meeting record status changes to "Processing" and the system automatically starts transcription.

Multi-language High-accuracy Transcription

Offline mode uses a high-accuracy speech recognition engine (such as WhisperX), which provides higher recognition accuracy compared to live mode:

  • Supports multi-language recognition

  • Higher recognition accuracy than live transcription

  • Ideal for important meetings that require precise records

Speaker Identification and Management

Offline mode supports automatic Speaker Diarization, where the system automatically distinguishes between different speakers:

  • Auto Identification: The system automatically labels different speakers (e.g., SPEAKER_00, SPEAKER_01)

  • Custom Names: Replace system labels with real names (e.g., "Manager Zhang", "Team Lead Li")

  • Management Interface: Manage all speaker label names in one place

After modifying speaker labels, all related segments in the transcript are updated simultaneously.

High-accuracy Timeline Recognition

Each transcribed text segment includes precise start and end times, allowing you to:

  • Pinpoint the exact time of each utterance

  • Sync with the audio player for jump navigation

  • Export as SRT subtitle files with timestamps

Dynamic Subtitle Playback

Offline mode provides dynamic subtitle playback that syncs the audio player with the transcript:

  • Sync Highlighting: During audio playback, the current transcript segment is automatically highlighted

  • Click to Jump: Click any transcript segment to jump the audio to the corresponding time point

  • Search and Navigate: After searching for a keyword, jump directly to that segment's audio position

This feature lets you quickly find specific discussion content in a meeting without listening to the entire recording from the beginning.

Last updated

Was this helpful?