File & Media Transcription

Convert long audio recordings, meeting files, interviews, podcasts, and online media streams into structured, synchronized subtitles.

Input Modes

1. Local Media Files

Drag and drop single or multiple audio/video files directly into DuRT.
Supported file formats: .mp3, .wav, .m4a, .flac, .aac, .ogg, .mp4, .mov, .mkv, .webm, .avi.
Batch processing allows transcribing multiple hours of recordings in the background.

2. Online Media & Direct Links

Paste links from mainstream video sharing platforms or direct .mp3/.mp4 media URLs.
Automatic stream extraction and server-side/client-side audio demuxing.

Advanced Capabilities

Word-Level Timestamps

Outputs millisecond-precise start and end times for every single word.
Ideal for karaoke-style subtitle animations, precise video cut points, and word search in video editors.

Speaker Diarization (Multi-Speaker Separation)

Automatically separates and labels different speakers (Speaker 0, Speaker 1, Speaker 2, etc.).
Unsupervised clustering: No pre-recorded voice samples required.
Perfect for multi-person interviews, boardroom meetings, and panel podcasts.

Exporting Subtitles

Transcribed results can be exported in multiple industry-standard formats:

SRT (.srt): Universal format compatible with Premiere Pro, Final Cut Pro, DaVinci Resolve, and VLC.
WebVTT (.vtt): Standard format for web HTML5 players.
Plain Text (.txt): Clean, formatted text document without timecodes.
JSON (.json): Structured data including words, timestamps, and speaker metadata for developers.