Skip to content
Convertto

AI That Runs In Your Browser

Remove backgrounds, transcribe audio, generate speech, upscale images and embed text — with the model running on your own device.

Convertto's on-device AI tools download an open model once, cache it, and then run it in your browser using WebGPU or WebAssembly. Background removal, speech recognition, text-to-speech, image upscaling, embeddings and classification all execute locally, which means your files are never uploaded and the tools keep working offline after the first run.

14 tools in this category

All on-device ai

AI Alt Text GeneratorDescribe an image with a captioning model running in your browser — a first draft for the alt attribute you then edit.
AI Audio TranscriptionRun Whisper locally to turn speech into text, SRT, VTT or a timestamped transcript. Works offline after the first run.
AI Background RemoverCut the subject out of a photo with a real segmentation model that runs in your browser. No upload, no sign-up, no watermark.
AI Content DetectorScore text with a real language model in your browser and see the per-token surprise that detection methods are built on.
AI Photo RedactorDetect people, faces, plates and screens with an object-detection model in your browser, then blur or black them out.
AI Text SummarizerCondense an article into a few sentences with a summarisation model running locally — nothing uploaded, no limit.
AI Text to SpeechTurn text into natural speech with a neural voice running in your browser, and download the audio as a WAV file.
Chat with Any DocumentAsk questions about a PDF, Word file, spreadsheet, CSV, Markdown or text file and get answers with the passage each came from.
Chat with Excel & CSVAsk questions about a spreadsheet in plain English and get answers with the sheet and row they came from. Runs entirely in your browser.
Chat with PDFAsk questions about any PDF and get answers with the page each one came from. The model runs in your browser — the file is never uploaded.
Chat with Word DocumentAsk questions about a Word document and get answers with the heading each came from. Runs on your device — nothing is uploaded.
Room Design VisualizerClick any wall, floor or piece of furniture in your own photo, then repaint it, remove it, or swap in a different product — all in your browser.
Semantic Search & SimilarityEmbed a list of sentences with a real model and rank them by meaning — or find the near-duplicates in a list.
Zero-Shot Text ClassifierGive a model any set of categories and it sorts your text into them — no training data, no fine-tuning, no API key.

Frequently asked questions

Is my file uploaded anywhere?

No. The model comes to your device rather than your file going to a server. After the weights download the first time, inference runs entirely in your browser — you can disconnect from the network and the tool still works.

Why is the first run slow?

The model weights have to download once, typically 25–200 MB depending on the tool. They are then stored in your browser cache, so every later run starts immediately. The size is shown on each tool before you begin.

Do I need a special GPU?

No. These tools use WebGPU when your browser exposes it, which is dramatically faster, and fall back to WebAssembly on the CPU when it does not. The fallback is slower but produces identical output.

Share on-device ai

People also search for

  • alt text generator
  • ai alt text
  • image caption generator
  • accessibility alt text
  • describe image ai
  • automatic alt text
  • seo image alt
  • free alt text tool
  • audio transcription free
  • whisper online
  • speech to text browser
  • transcribe audio privately
  • audio to srt
  • video to subtitles
  • offline transcription
  • local whisper
  • mp3 to text
  • transcribe interview
  • ai background remover
  • remove background from image
  • transparent background
  • background eraser free
  • remove bg
  • cutout image