Qiaomu Clipper adds video subtitle transcription; ByteDance ASR tops tests
vista8 · x · 2026-10-06
- vista8 built a new feature for Qiaomu Clipper (open-source Chrome extension, 137 stars) that transcribes audio/video from nearly any site including YouTube and Bilibili, letting users generate transcripts for subtitle-less videos and study immersively.
- He benchmarked multiple cloud ASR services: ByteDance Speech (turbo), Qwen3-ASR on SiliconFlow, GLM-ASR-2512, Step 2.5 ASR, and Xiaomi MiMo-ASR. Per Opus 5.5's feedback, ByteDance Speech performed best, with millisecond-level timestamps and fast speed.
- Roadmap includes local Whisper and local Qwen3 ASR plus support for various cloud speech-to-text APIs. Setup is done by pasting an install prompt into Codex, Workbuddy, or Doubao to configure a local assistant.
Related event: Qiaomu Clipper Adds Audio/Video Transcription for Obsidian Users(2 posts)→
More from coding & agent
- DeepSeek-style agent infrastructure ran 1.3B sandboxes in 4 weeks, peaking at 170K concurrent — teortaxesTex · 2026-10-06
- "A single Claude Code session won't replace your software": a reality check on the one-shot AI narrative — seatedro · 2026-10-06
- Your evals are your product spec: the most common mistake AI product teams make — realmadhuguru · 2026-10-06
- Dev's Ultrafast review: 6x token cost, $500 plan hits weekly limits every 1-2 days — holdenmatt · 2026-10-06
- dotey open-sources the info-digest Agent Skill behind his viral news-digest screenshots — dotey · 2026-10-06
- Google's Cogentic multi-agent system produces novel results on 5 open research problems — Dr_Singularity · 2026-10-06