Repository navigation
Add local speech with optional cloud voice - #6
Merged
Merged
Conversation
Jonathan listens and speaks through the selected microphone and speaker, including Bluetooth on Windows WASAPI and Linux PulseAudio or PipeWire. Faster-whisper and Piper stay on the machine unless OpenAI or xAI is chosen, and model downloads are limited to Hugging Face and the official sources with checksums. Co-authored-by: Admin <GoDeskio@users.noreply.github.com>
cursor
Bot
force-pushed
the
cursor/voice-local-3ce6
branch
from
October 10, 2026 04:06
30f80ad to
8ef3850
Compare
GoDeskio
marked this pull request as ready for review
October 10, 2026 04:49
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Jonathan Ai can talk through the microphone and speaker, including a Bluetooth headset, on Windows (WASAPI) and Linux (PulseAudio or PipeWire).
Speech-to-text defaults to local faster-whisper. Text-to-speech defaults to local Piper. OpenAI and xAI are used only after they are selected in
/voiceor the settings panel. Push-to-talk is on by default. The wake word is optional and stays on this machine. Model files come from Hugging Face or the official Piper and Whisper sources and are checked with SHA-256. The voice packages are an optional extra:pip install "clawd-codex[voice]".The dispatch shape follows Octop's voice manager and is credited in NOTICE. Browser, Edge, Tencent, and MiMo presets are not included.
Product tie: Jonathan Ai speaks and listens on the local mic, speaker, or Bluetooth headset, and audio stays on the machine unless OpenAI or xAI is chosen.