CodeIssuesPull RequestsActionsSecurityInsights
✨ AI
More
Settings

Phase 2: On-device Whisper — no API, no internet, no cost #4000

Merged⚡ AI-generatedXSccantynz wants to mergeclaude/phase2-local-aimainopened Mar 27, 2026
ccantynzcommented Mar 27, 2026

Originally written by @ccantynz-alt on GitHub.
Imported from https://github.com/ccantynz-alt/48co.v1/pull/37


Phase 2: On-Device Whisper — Zero API Keys

Users can now use voice-to-text with ZERO API keys, ZERO internet, ZERO cost per use.

How it works

  1. User turns on "Local Voice" in Settings
  2. Picks a model size (75MB to 1.6GB)
  3. Downloads once
  4. All transcription runs on their device from then on

New files

  • local_whisper.rs — whisper.cpp integration via whisper-rs
  • Updated lib.rs — local vs API branching
  • Updated App.jsx — model download UI

https://claude.ai/code/session_01PBeNmPHrD2W6A2YKZRC7V3

ccantynzcommented Mar 27, 2026

Originally written by @vercel[bot] on GitHub.


The latest updates on your projects. Learn more about Vercel for GitHub.

Project Deployment Actions Updated (UTC)
48co-ai-pa Error Error Mar 27, 2026 0:29am

Request Review

Cross-repo impact

See what breaks downstream if this PR merges.

Analyze →
⮌ Merged

This pull request was merged into main.

c comment · e edit title · m merge · a approve · r request changes · ? shortcuts