#3333rd of 81 in VoiceFor image, video and design, video and animation, voice, speech and music
auto-subs
Offline subtitle generator with Resolve, Premiere Pro and After Effects integration
- Stars
- 4.5k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Sep 2026
- Language
- TypeScript
3,202 on 21 Apr 20264,544 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
AutoSubs is a desktop app that transcribes audio or video to timestamped subtitles on-device, using Whisper (GGML), Moonshine, Parakeet, Canary, SenseVoice and other ONNX models downloaded on demand. It labels speakers via diarization, exports SRT or text, and can send styled subtitles into DaVinci Resolve, Premiere Pro and After Effects. A CLI is also available.
Who it is for: Video editors needing local subtitles, especially Resolve or Adobe users
Strengths
- Runs fully offline; models downloaded on demand from an in-app Model Manager
- Many engines: Whisper, Moonshine, Parakeet, Canary, SenseVoice, Cohere, GigaAM, Omni-ASR
- Direct integration with DaVinci Resolve, Premiere Pro and After Effects
- Speaker diarization and a CLI alongside the GUI
Weaknesses
- Optional MMS word-alignment weights are CC BY-NC 4.0, noncommercial only
- Mac App Store build of DaVinci Resolve is not supported
- Larger models need much memory, e.g. Whisper large-v3 about 10 GB RAM
- Standalone export lists only SRT, text and clipboard
What it needs
- RAM ≥ 1 GB
- Needs DaVinci Resolve (optional), Adobe Premiere Pro / After Effects (optional)
- Models: Whisper (GGML), Moonshine, Parakeet, Canary, SenseVoice
Quick answers
Is auto-subs open source?
Yes. Its code is on GitHub under the MIT license.
Also in Voice
See all 81| Rank | Project | Score |
|---|---|---|
| 1 | voicestudioDesktop app for voice cloning, dubbing, dictation and audiobooks | 98 out of 100 |
| 2 | handyOffline push-to-talk dictation app that pastes transcripts into any text field | 91 out of 100 |
| 3 | whisper.cppC/C++ speech-to-text engine running OpenAI Whisper models locally | 90 out of 100 |
| #4 | xiaozhi-esp32ESP32 firmware for a voice chatbot with MCP device and cloud tool control | 83 out of 100 |
| #5 | buzzOffline desktop app for transcribing and translating audio with Whisper | 83 out of 100 |