Voice mode enables real-time spoken conversations with AI. Speak naturally and receive spoken responses — all processed locally on your device.

Overview

Voice mode combines:
  • Speech recognition — Converts your voice to text
  • AI chat — Processes your message and generates a response
  • Text-to-speech — Speaks the response back to you
Everything runs locally with no cloud services.

Getting Started

Open Voice in the sidebar. The first time, Izwi lists the models voice needs and downloads them with one click. Models load when you start a conversation, so there is no separate load step. Voice has two engines, chosen in Voice settings › Engine: To download them from the command line instead:

Using Voice Mode

  1. Navigate to Voice in the sidebar
  2. Click Start talking (or press Space) and allow microphone access if asked
  3. Speak naturally; Izwi answers when you pause
  4. Start talking while Izwi speaks to interrupt it
  5. Click End (or press Space) when you are done

Controls


Voice Settings

  • Voice — Choose the assistant’s voice; press play to hear a preview
  • Instructions — How the assistant should answer. Saved when you leave the field and used from your next conversation; Reset to default restores the original
  • Memory — When on, Izwi remembers lasting preferences and facts you mention. Manage memories lists them so you can forget one or all
  • Engine — Standard or Compact, the status of its models, and a button to load or unload them
Turn detection is automatic: the server ends your turn after a short silence. Steady background noise does not start a turn, and a cough or noise burst while Izwi talks lowers its volume instead of cutting it off.

API Routes

Voice mode uses preview APIs for the voice profile, observations, saved sessions, and low-latency WebSocket transport. See the API Reference for persisted voice state and Voice Realtime for the WebSocket protocol. LFM3-Audio-2B-GGUF answers spoken turns with interleaved text and speech, through the same speech-to-speech routes as LFM2.5-Audio-1.5B-GGUF: name either as s2s_model_id in the WebSocket’s unified mode. The Compact engine uses LFM3-Audio-2B-GGUF by default, which picks its own voice in conversation. LFM2.5 Audio stays selectable in Voice settings › Engine, with its four voices, and with only LFM2.5 Audio downloaded the Compact engine uses it. A spoken turn can call tools when its model can: a chat model that calls tools (Qwen3, Qwen3.5, LFM2.5, LFM3) in the modular pipeline, or LFM3 Audio. It may call the server’s built-in tools (the local date and time; on by default with LFM3 Audio, on request in the modular pipeline), function tools a WebSocket client declares in input_stream_start and answers with function_call_output, and the tools of MCP servers the session names. The reply calls a tool, reads its result, then speaks the answer. See Voice Realtime for the fields and events. Tools, tool servers, agents that hand over to each other, and the switches for how Izwi takes turns are set in Voice settings. The Voice agents guide walks through them.

Tips for Best Results

  1. Use a good microphone — Built-in laptop mics work but external mics are better
  2. Minimize background noise — Find a quiet environment
  3. Speak clearly — Natural pace, clear pronunciation
  4. Wait for responses — Let the AI finish before speaking again

Keyboard Shortcuts

Shortcuts are ignored while focus is inside a text field or on a button.

Troubleshooting

No audio input detected

  1. Check your microphone permissions in system settings
  2. Ensure the correct input device is selected
  3. Test your microphone in another application

”Couldn’t load the voice models”

The models do not fit in the memory Izwi can use alongside the other models it has loaded. Unload models you are not using on the Models page, or switch to the Compact engine in Voice settings › Engine.

Responses are slow

  1. The first reply after starting includes loading the models; later replies are faster
  2. Try the Compact engine
  3. Check system resources (RAM, CPU usage)

Poor transcription accuracy

  1. Speak more clearly and slowly
  2. Reduce background noise
  3. Use an external microphone

See Also