Voice Input and Read Aloud
LanMate supports three voice workflows: hold-to-talk (speech to text), voice conversation (continuous dialogue with playback), and read-aloud (text to speech). Local engines first — transcribed and synthesized text never leaves your machine.
Hold to Talk
The microphone button on the right of the input: hold to speak, release to transcribe:
- The transcript can be sent directly, or filled into the input for editing first (configurable in settings)
- Too-short clips are rejected — no empty messages
- Requires a transcription engine configured under Settings → Voice Transcription & Synthesis
Great for when your hands are busy, or when speaking is faster than typing.
Voice Conversation
The “Voice Conversation” button on the input enters a full-screen voice mode:
- Speak; a detected pause sends automatically
- Agent status shows while thinking
- Replies are spoken automatically
- Speak during playback to interrupt — no need to wait
The whole thing flows like a phone call. Live captions show everything you said and every reply on screen.
Read Aloud
The read-aloud button on a message speaks the text. Settings offer:
- Auto-read: read the running text stream, or only the final reply
- Voice: preset voices with previews, or describe it naturally (“a deep, calm male voice”)
- Local synthesis: run the synthesis model on your machine — read text never leaves it
Engine Setup
Settings → Voice Transcription & Synthesis:
| Engine | Used for | Notes |
|---|---|---|
| Transcription model | Hold-to-talk, voice attachments | Local Whisper one-click install (deps + model), or a FunASR-compatible endpoint |
| Real-time transcription | Voice conversation | Continuous recognition, low-latency; off disables the voice-conversation entry |
| Synthesis model | Read aloud | Local engine (works offline once set up), or a third-party service |
Local Whisper install: when unconfigured, the settings page shows an “Install” button that installs dependencies into the shared environment and streams the model download (auto-falls-back to a mirror on failure), with live progress.
Lansenger Voice Messages
Voice messages received via Lansenger channels are auto-transcribed and enter context with the attachment. Send voice from the channel; the desktop handles it.