A model is still running

A model is still running or downloading. Leaving will stop the current operation. Stay on this page to let it finish.

Skip to content
LocalAI.toolsBeta

Join the waitlist

Get an email when the new apps and model runs launch.

No account needed.

Back to apps

Local AI SRT / Subtitles Generator

Featured App

Transcribe, translate, and style subtitles—all on your device.

About this app

Transcribe audio or video into timed subtitles, then edit, translate, and style them alongside your media. Export SRT, VTT, or ASS files, or render a video with captions built in.

Local InferenceUnlimited RunsPrivate Environment

Transcribe audio and video

Turn speech into timed subtitles. Choose a local model and language; the app tests your device before the first run.

Edit with your media

Play your media while editing subtitle text and timing. Fine-tune word boundaries where supported, with undo and redo.

Translate subtitle tracks

Translate a full track or selected subtitles. Keep each language in its own track for review and editing.

Refine timing and speakers

Refine timing with alignment models and add speaker labels. Review the results before applying them.

Style your captions

Choose a preset or customize fonts, colors, and placement. Preview changes across a track or on one subtitle.

Control subtitle grouping

Control subtitle length, word count, and line breaks. Split at pauses and sentences to keep captions readable.

Export subtitle files

Save SRT, VTT, or styled ASS files. Export transcripts or JSON, including word and speaker details when available.

Burn captions into video

Save a video with styled captions built in. Your original media stays separate.

Keep projects on your device

Reopen your media, tracks, styles, and saved runs. Projects stay in this browser, with local storage controls.

Get Started

  1. 01

    Add Your Media

    Create a project and choose an audio or video file.

  2. 02

    Generate Subtitles

    Choose a model and language, then generate subtitles. The app downloads the model and tests your device on first use.

  3. 03

    Refine & Export

    Check the text and timing, add translations or styling, then download subtitles or a captioned video.

Get notified at launch

We’ll email you when Local AI SRT / Subtitles Generator is ready.

Powered by local models 26

Browser
Qwen / Alibaba Cloud

Align a matching English transcript to audio locally in the browser. Returns complete word boundaries; Q4 WebGPU recommended, WASM CPU fallback measured independently.

Released
Jan 29, 2026
1 variantWord-level audio alignment
Desktop
Qwen / Alibaba Cloud

Align an existing transcript to mono audio and estimate word/character start and end times using the official non-autoregressive 5000-class timestamp head. Does not transcribe unknown speech.

Released
Jan 29, 2026
1 variantWord-level audio alignment
Desktop

Canary 2

Coming soon
NVIDIA

Align a matching transcript to its recording with the auxiliary CTC checkpoint distributed with NVIDIA Canary 2.

Released
Aug 8, 2025
1 variantWord-level audio alignment
Browser

OPUS-MT

Coming soon
Helsinki-NLP / University of Helsinki

Translate English text into Spanish and return the translated text. This worker supports only English-to-Spanish translation, not automatic language detection or other language pairs.

Repository created
Mar 2, 2022
1 variantTranslation (MT)
Desktop

TranslateGemma

Coming soon
Google

Translate text or text visible in still images locally. Supply source and target language codes; review OCR, names, numbers and omissions.

Released
Jan 15, 2026
3 variantsTranslation (MT)
Browser

HY-MT 1.5

Coming soon
Tencent Hunyuan

Translate short text in four verified directions: English→Spanish, Spanish→English, English→French and Chinese→English. Tencent’s community license applies; review every translation.

Released
Dec 30, 2025
1 variantTranslation (MT)
Desktop
Tencent Hunyuan

Translate short multilingual text locally with the original HY-MT1.5 1.8B checkpoint and official source-aware translation prompt.

Released
Dec 30, 2025
2 variantsTranslation (MT)
Desktop

Hy-MT 2

Coming soon
Tencent Hunyuan

Translate text locally with Tencent Hy-MT2 1.8B using explicit language selections and the official translation prompt.

Released
May 21, 2026
2 variantsTranslation (MT)
Desktop
Tether AI Research

Local English to French translation using the original FP32 EuroNano Base checkpoint.

Repository created
May 4, 2026
4 variantsTranslation (MT)
Desktop

Qwen3.5 Desktop

Coming soon
Qwen / Alibaba Cloud

Run local text questions, still-image questions using Qwen3.5 4B Desktop. Answers can hallucinate or miss visual details.

Released
Mar 2, 2026
2 variantsLLM · Chat & text
Browser

LFM 2.5

Coming soon
Liquid AI

Ask questions, draft short text, and experiment with multilingual conversations using a compact chat model. Returns an assistant reply; complex reasoning and factual answers need review.

Released
Jan 5, 2026
3 variantsLLM · Chat & text
Browser

Apertus 1.1

Coming soon
Swiss AI Initiative (ETH Zurich / EPFL)

Ask questions, draft short text, or continue a conversation with a compact multilingual chat model. Returns an assistant reply; answers can be inaccurate and should be checked.

Repository created
May 1, 2026
1 variantLLM · Chat & text
Browser

Qwen3.5

Coming soon
Qwen / Alibaba Cloud

Chat with text or images locally using Qwen3.5.

Released
Mar 2, 2026
1 variantLLM · Chat & text
Browser

Gemma 4

Coming soon
Google

Chat with text, images or WAV audio using the complete Gemma 4 E2B and E4B checkpoints on verified configurations.

Released
Mar 31, 2026
2 variantsLLM · Chat & text
Desktop
NVIDIA

Transcribe speech with punctuation and approximate word-level timestamps. Native multilingual FastConformer/TDT decoding retains complete token timings and durations.

Released
Aug 14, 2025
1 variantSpeech to text (ASR)
Desktop
Microsoft

Transcribe authorized WAV files locally with the 1.5B streaming checkpoint. Native speaker-prefixed text and complete chunk outputs arrive progressively; hotword context is optional.

Released
Sep 3, 2026
1 variantSpeech to text (ASR)
Desktop
OpenAI

Transcribe WAV audio locally with word-level timestamps in seconds.

Released
Oct 1, 2024
1 variantSpeech to text (ASR)
Browser

Parakeet TDT 3

Coming soon
NVIDIA

Transcribe speech locally in your browser with NVIDIA Parakeet TDT 0.6B v3. Returns punctuation, word and token timestamps, confidence scores and the complete native result.

Released
Aug 14, 2025
1 variantSpeech to text (ASR)
Browser

Wav2Vec2 ASR

Coming soon
Meta

English speech recognition with word-level CTC emission timestamps. Returns transcript, complete word timings and model confidence; no speaker labels or translation.

Repository created
Mar 2, 2022
1 variantSpeech to text (ASR)
Browser

Whisper Original

Coming soon
OpenAI

Multilingual transcription, English translation, and optional timestamps.

Released
Sep 21, 2022
3 variantsSpeech to text (ASR)
Browser

Whisper 3

Coming soon
OpenAI

Multilingual transcription, English translation, and optional timestamps.

Repository created
Oct 1, 2024
1 variantSpeech to text (ASR)
Desktop

Nemotron ASR 3.5

Coming soon
NVIDIA

Transcribe local audio progressively with NVIDIA’s multilingual RNNT model. Returns complete text, approximate word-level timestamps and the native recognition result.

Released
Jun 4, 2026
1 variantSpeech to text (ASR)
Desktop
pyannote

Estimate who spoke when locally using pyannote Community-1. Returns regular and exclusive speaker-turn timelines with anonymous speaker labels, not names or transcripts.

Repository created
Apr 15, 2025
1 variantSpeaker diarization
Browser

Sherpa-ONNX

Coming soon
k2-fsa / pyannote / 3D-Speaker

Identify anonymous speaker turns locally with pyannote segmentation and3D-Speaker embeddings. Returns a complete speaker timeline; WASM CPU only.

Repository created
Sep 1, 2022
1 variantSpeaker diarization
Desktop

Sortformer 2.1

Coming soon
NVIDIA

Identify up to four speaker channels in speech recordings with incremental timed segments.

Repository created
Oct 22, 2025
1 variantSpeaker diarization
Desktop
NVIDIA

Estimate anonymous speaker turns from complete WAV recordings with the native eight-channel Nemotron3 diarization model.

Released
Sep 23, 2026
1 variantSpeaker diarization