Starstruk Logo MarkStarstruk

v3.1.7

thewh1teagle/vibev3.1.7Sep 4, 2026by github-actions[bot]

AI Summary

This release introduces the ability to name speakers directly in transcripts and reassign lines to specific speakers. It also improves engine compatibility by fixing prompt issues with Parakeet and Nemotron, adds batch link processing, and resolves Windows compatibility bugs with non-Latin titles.

Key Highlights

  • Name your speakers directly in the transcript to update labels across all exports (text, Markdown, PDF, etc.).
  • Reassign lines to different speakers or create new speakers for unassigned lines using a popover.
  • Transcribe several video links in one go using a new queue system.
  • Fixed compatibility so Whisper prompts no longer block Parakeet or Nemotron engines.
  • Resolved Windows compatibility issues where non-Latin video titles caused download failures.

New Features

  • Speaker Naming: Click a 'Speaker 1' label to type a custom name that persists across exports.
  • Speaker Reassignment: Move lines between speakers or assign speakers to previously unlabelled lines.
  • Batch Link Processing: Paste multiple links or add them one by one to a queue.
  • Engine Compatibility: Automatically skips prompts for models like Parakeet and Nemotron that don't support them.

Full Release Notes

What's new? 🎉📣

- 🗣️ **Name your speakers** — click a "Speaker 1" label in a finished transcript and type a name. It replaces the label on every line of that speaker, on screen and in every export (text, Markdown, HTML, SRT, VTT, PDF, DOCX; JSON keeps the index and adds `speakerName`). Names are saved with the project, so they are there when you reopen it
- 🎯 **Put a line on the right speaker** — the same popover moves one line to another speaker, or to a new one. A short line that diarization left with no speaker at all now shows a dashed placeholder so it can be given one. Sona 0.6.2 also attributes such lines to the nearest speaker turn within 1.5 seconds, so far fewer arrive unlabelled in the first place
- 🦜 **A Whisper prompt no longer blocks Parakeet or Nemotron** — those engines take no prompt, and a saved one made every run fail with "does not support text prompts". The prompt is now left out of the request when the loaded model reports it cannot use it (the translate switch too), so it stays saved for when you switch back to Whisper. The Settings prompt field says so when the selected model ignores it
- 🔗 **Transcribe several links in one go** — paste a batch of links into the link box, or add them one by one with the plus button, and they queue up in a list under it. They download in turn; one that fails is skipped and listed at the end, and the rest go straight to transcription. The box clears as soon as the run starts
- 🪟 **Links with non-Latin titles no longer fail on Windows** — yt-dlp can print bytes that are not UTF-8, and reading its output aborted the whole download on the first one. Thanks to @mikemikimike (#1473)

Signed and notarized on macOS and Windows.

**Full Changelog**: https://github.com/thewh1teagle/vibe/compare/v3.1.6...v3.1.7