localvoxtral
Reduces context switching and typing overhead for developers working with Claude Code sessions by enabling voice input streamed directly into active terminal…
Talk to your coding agents by voice. Realtime, fully local macOS dictation that streams words as you speak and grounds LLM polishing in the exact Claude Code session under your cursor — Ghostty, iTerm2, Terminal.app, even a herdr pane. 100% on-device on Apple Silicon.
- Ask Claude to transcribe voice commands while coding without sending audio to cloud servers.
- Generate code faster by dictating function logic directly into your terminal session in real-time.
- Automate repetitive coding tasks by speaking instructions that ground into your active Claude Code session.
Reduces context switching and typing overhead for developers working with Claude Code sessions by enabling voice input streamed directly into active terminal windows, improving hands-free workflow efficiency on macOS.
Engineering teams using Claude Code on Apple Silicon Macs who need faster iteration through voice-driven agent interaction.
https://github.com/T0mSIlver/localvoxtral
By T0mSIlver
How to Get It
claude plugins install T0mSIlver/localvoxtral
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
Auto-generated from the tool's public listing — not hands-on verified. Cross-check against the source repo's README before running.
After installing, paste this into Claude:
Transcribe voice commands while coding without sending audio to cloud servers
Trust Signals Auto-scanned
Community Pulse Growing
Discussed on Hacker News
- Show HN: Localvoxtral – Local real-time dictation on macOS with streaming STT — Hacker News · 1 pts
1 mentions across 1 sources
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 58 GitHub stars; contributors unknown; last commit 0d ago; license MIT.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 58 GitHub stars; contributors unknown; last commit 0d ago; license MIT.