-
Frame Voice v0.1.1 Stable
DieMitchell released this
2026-10-10 23:08:36 +02:00 | 4 commits to main since this releaseFrame Voice v0.1.1
- The tray uses a white microphone with the Frame corner mark. Disabled dictation uses the same white icon with its existing cross. Headset recording/cancellation colours are unchanged.
- New installations use right-controller X for Clear, matching left D-pad Left. This avoids B's native Desktop space. Existing configured button choices are retained; select X in Controllers to change them.
- Default X clears exactly the tracked dictation and its separator, without an extra controller Backspace. Optional native-space handling applies only when B is explicitly selected.
- User docs now separate settings, troubleshooting, removal, and developer references, with a configuration screenshot and a concise transcription comparison.
Updates preserve saved settings, API keys, and downloaded models. Open Configure → General → Check for updates.
Downloads
-
Frame Voice v0.1.0 Stable
2026-10-10 23:08:38 +02:00 | 8 commits to main since this releaseFrame Voice v0.1.0
These notes describe v0.1.0. Current versions default to X for Clear and white
tray icons; see v0.1.1. Existing saved bindings are preserved.First stable release of controller-driven dictation for Steam Frame.
- Tap, release, then hold a joystick cap to dictate into Desktop or standalone apps. Click during recording to cancel; use A to submit and release B to clear.
- Choose Groq cloud transcription or offline Local Fast/Balanced models, with automatic detection and 99 language choices.
- Configure General, Transcription, and Controllers in a dark tabbed window, then save once. Customize or reset the Groq cleanup prompt.
- Blue tray microphone when running, red crossed-out microphone when paused. Activation animation accounts for microphone and speaker startup; feedback streams close after use.
- Silence checks combine ambient noise, cue filtering, voice activity, and Groq confidence metadata to reduce invented transcripts.
- Version/build information, manual update checks in General, and guided updates that preserve configuration and models.
- GUI, terminal-menu, and noninteractive installation. Delete unused downloaded models, or uninstall with separate configuration/model retention choices.
- Updates preserve settings and provide rollback snapshots. Release assets include checksums and separately licensed runtime helpers and sources.
Install
Open Desktop → Konsole on your Frame and run:
curl -fsSL https://raw.githubusercontent.com/techieyann/frame-voice/main/get.sh | shCurrent limits
Dictation works in desktop applications, not the Steam dashboard or VR games.
Accented and non-Latin text requires a clipboard-compatible standalone app;
nested Desktop typing currently supports ASCII. Default Desktop B inserts a space;
Clear accounts for it, with a setting for customized B mappings. Desktop Clear tracks text inserted
by the running daemon, including its trailing space; restarting resets that count.
Speech detection and transcription can still mistake environmental sounds for voice.See the README for setup and usage.
Downloads
-
v0.1.0-experimental.2 Pre-Release
2026-10-10 23:08:41 +02:00 | 12 commits to main since this releaseDownloads
-
v0.1.0-experimental.1 Pre-Release
2026-10-10 23:08:43 +02:00 | 12 commits to main since this releaseDownloads
mirror of
https://github.com/techieyann/frame-voice.git
synced 2026-10-17 17:01:35 +02:00