Bolo Voice · Realtime AI Voice Agent

Bolo Voice

A real-time AI voice agent by Bolo App. Talk naturally — in Urdu, English, and 50+ languages.

Tap to start

Voice Language

camera

Conversation

About

Bolo Voice is a real-time AI voice agent by Bolo App. It chains specialized models — speech detection, transcription, a language model, and voice synthesis — so conversations feel human and every stage can be tuned. The speech-to-text and voice models run on the Bolo Voice Service; the brain runs on a local GPU with mistral.rs.

Learn more at boloapp.ai

The pipeline

You speak
VAD detects speech silero-vad
STT transcribes it Bolo Voice · Whisper ASR
LLM analyses and composes the reply · local GPU Qwen/Qwen3-14B · mistral.rs
TTS speaks it back Bolo Voice · OmniVoice
The orb replies

Settings

Speech-to-speech server URL URL of your speech-to-speech server, e.g. http://localhost:8080 (the app adds /v1/realtime). Transport How audio travels to the server. Applies on the next conversation. Microphone Applies on the next conversation (or Restart). Speakers Where assistant audio plays. Chrome/Edge support switching outputs.

Noise gate Off

Off −3 dB

Mutes the mic below the handle so room noise isn't sent. Slide fully left to turn it off; the bar shows your live input while in a call.

Instructions

Connect first, then come back here to apply live changes.

Tools

Let the assistant act during the conversation. Changes apply live.

Web search Look things up on Google, via Serper.

Search API key

Camera Let the assistant see through your webcam.

A live preview shows bottom-left while the camera is on.