On-device subtitle generation that connects directly to DaVinci Resolve, Premiere, and After Effects.
On-device subtitle generation that connects directly to DaVinci Resolve, Premiere, and After Effects.
Local-first AI subtitles. No cloud, no subscription, no data leaving your machine.
Use it as a standalone app, or connect to DaVinci Resolve, Adobe Premiere Pro, and After Effects.
macOS users can also install AutoSubs with Homebrew:
brew install --cask auto-subs
Debian/Ubuntu (.deb):
wget https://github.com/tmoroney/auto-subs/releases/latest/download/AutoSubs-linux-x86_64.deb
sudo apt install ./AutoSubs-linux-x86_64.deb
Fedora/openSUSE (.rpm): Download AutoSubs-linux-x86_64.rpm and open it with your package manager.
[!WARNING] Mac App Store version not supported - download DaVinci Resolve from blackmagicdesign.com instead.
For command-line usage, see the CLI Guide with complete reference, examples, and troubleshooting.
[!TIP] I highly recommend checking out DeepWiki for asking questions and understanding the codebase.
AutoSubs ships with several local transcription model families. All run fully on-device — nothing is sent to the cloud. Models are downloaded on demand from the in-app Model Manager.
Accuracy is a relative 1–4 rating within AutoSubs (higher is better). Sizes and RAM figures are approximate.
OpenAI's Whisper, via whisper-rs (GGML). Each size is available in a multilingual variant and an .en English-only variant (the .en models are slightly more accurate on English audio).
Useful Sensors' Moonshine, via ONNX Runtime. The tiny English model is quantized; the language-specific tiny variants and the base model are float-precision.
NVIDIA's Parakeet-TDT-0.6B-v3 (int8 ONNX). Fast and accurate, with support for 25 European languages plus Russian and Ukrainian. Orukeet is a community variant on the same engine — faster and more accurate than Parakeet, with weights under CC BY-SA 4.0.
Model Size RAM Languages Accuracy orukeet 672 MB 4 GB 25 languages (EU + RU + UK) ★★★★ parakeet 700 MB 2 GB 25 languages (EU + RU + UK) ★★★★Alibaba's SenseVoice (int8 ONNX). Compact and well-suited to CJK audio.
Model Size RAM Languages Accuracy sense-voice 230 MB 1 GB Chinese, English, Japanese, Korean, Cantonese ★★★NVIDIA's Canary-1B-v2 (int8 ONNX). A multilingual encoder-decoder model that also supports native translation.
Model Size RAM Languages Accuracy canary 1 GB 3 GB 25 languages (EU + RU + UK) ★★★★Cohere Transcribe (int4 ONNX). The highest-accuracy option for a focused set of 14 widely-spoken languages.
Model Size RAM Languages Accuracy cohere 2 GB 4 GB Arabic, German, Greek, English, Spanish, French, Italian, Japanese, Korean, Dutch, Polish, Portuguese, Vietnamese, Chinese ★★★★Sber's GigaAM v3 (int8 ONNX). A Conformer model trained on 700k hours of Russian speech — the most accurate option for Russian audio. The end-to-end CTC variant outputs punctuated, normalized text.
Model Size RAM Languages Accuracy gigaam-v3 225 MB 2 GB Russian, English ★★★★GigaAM Multilingual (600M, int8 ONNX) covers Central Asian languages that the other models handle poorly — Whisper large v3 scores 58–110% WER on Kazakh, Kyrgyz and Uzbek. It uses a character-wise CTC head, so unlike GigaAM v3 its output has no punctuation or capitalization.
Model Size RAM Languages Accuracy gigaam-multilingual 592 MB 3 GB Russian, Kazakh, Kyrgyz, Uzbek, English ★★★★Meta's Omnilingual ASR (1B CTC, fp32 ONNX). Covers 1600+ languages, making it the fallback for languages no specialist model supports. Output is lowercase with no punctuation.
Model Size RAM Languages Accuracy omni-asr-1b-ctc 3.7 GB 4 GB 1600+ languages ★★★In addition to transcription models, AutoSubs downloads a speaker diarization model (~40 MB, user-selectable from the Model Manager) and a Silero VAD model (auto-downloaded for voice activity detection during transcription). An optional MMS forced-alignment model (~320 MB, CC BY-NC 4.0) can also be downloaded for word-level timestamps — see Model licensing.
AutoSubs can run as a standalone subtitle generator, connect directly to DaVinci Resolve, or communicate with Adobe Premiere Pro and After Effects through the bundled CEP extension.
Select a Preset Style Or create your ownPRs are welcome! See CONTRIBUTING.md for how to get started, including the dev setup and a full codebase walkthrough via AutoSubs DeepWiki.
For detailed information about the DaVinci Resolve integration architecture, Lua server, Fusion macro system, and development workflow, see Resolve-Integration/README.md.
AutoSubs code is MIT-licensed. The optional MMS forced-alignment weights are downloaded separately and licensed under CC BY-NC 4.0 for noncommercial use. Users are responsible for ensuring their use complies with the model license.
The forced-aligner weights originate from Meta's MMS model, with forced-alignment conversion work by MahmoudAshraf and ONNX/INT8 conversion by onnx-community. Conversion and quantization changes were made by those respective projects; no endorsement is implied.
While MMS supports over a thousand languages, word-level alignment relies on romanizing the transcript with uroman. uroman covers the major world scripts (Latin, Cyrillic, Arabic, CJK, most Indic scripts, etc.), but very low-resource minority languages whose scripts are not included in its data may produce degraded or missing word timestamps.
AutoSubs is built on top of excellent open-source projects:
Resolve 21 (macOS, Apple Silicon): script starts its server but does not launch the app — client stays Disconnected
[Bug]: AutoSubs not working after Davinci Resolve 21 Update
[Bug] App crashes immediately when generating subtitles with Whisper Large on macOS
Crash (SIGABRT / ggml_abort) transcribing audio with no detectable silence gaps
[Bug]: autosubs not working on davinci 21.1(build 14)
[Bug]: Cannot connect to DaVinci Timeline (V21.1.0)
[Bug]: Failed to place all 22 subtitles — template clips had no Fusion composition. Check that your DaVinci Resolve version supports the AutoSubs Caption template.
[Bug]: Server handler failed
[Bug]: Transcription failed: Failed to download 'ggml-large-v3.bin' from 'ggerganov/whisper.cpp'
[Bug]: Transcription failed: Failed to download 'ggml-large-v3.bin' from 'ggerganov/whisper.cpp'