What VidiRelay is best for
VidiRelay is a transcription workspace aimed at people working with short-form and social video rather than meetings. You paste a public link from YouTube, YouTube Shorts, TikTok, Instagram Reels, or Facebook, or upload MP4, MOV, WebM, MP3, WAV, and M4A files, and it returns a transcript split into timestamped segments that you can edit, search, and label by speaker. Existing TXT, SRT, and VTT files can be brought in too. From the same transcript it can draft summaries, captions, hooks, and script rewrites, and export to TXT, SRT, VTT, CSV, JSON, or DOCX-ready text. Up to 50 links can be queued in one batch, and transcripts are organized in folders. Billing is credit-based rather than a subscription: one credit covers each started 10-minute block of a successful transcript, new accounts get 50 welcome credits, and packs start at $9.99 for 200 credits, with all credits valid for 12 months. Editing, exporting, sharing, and the content tools are included once a transcript exists.
- 50 welcome credits cover roughly 500 minutes of transcript, so the output can be judged before paying
- Credit packs are one-time purchases valid for 12 months rather than a monthly subscription, which suits irregular use
- Editing, exports, sharing, and the content tools are included once a transcript exists, so repurposing does not cost extra credits
- Six export formats including SRT and VTT, so the same transcript feeds subtitles and text workflows
- The site does not publish which spoken languages the transcription engine supports or any accuracy figure — test Korean audio with the welcome credits before buying
- Only reachable public links work; private, login-only, and local network videos are rejected
- Credits are consumed in whole 10-minute blocks, so a batch of short clips costs the same as much longer ones
- It is an independent third-party tool with no affiliation to YouTube, TikTok, Instagram, or Facebook, and you carry the rights responsibility for anything you submit
- Interface localization does not by itself confirm meeting-grade features such as diarization quality or live capture — it transcribes finished files and links, not live calls