Real-Time Voice + Camera
Hands-free AI conversations while you work — voice mode now pairs real-time audio with optional live camera streaming.
Voice mode goes hands-free
Voice mode now pairs real-time audio with optional live camera streaming. Ask questions while pointing your phone at the job, and Camera Search responds with spoken answers.
- Live voice conversations — powered by Pipecat and Daily, with natural turn-taking and no tap-to-talk required
- Optional camera streaming — enable your camera during a voice session so the AI can see what you see
- Live captions — real-time transcription with a typewriter-style display and glassmorphic overlay
- Context carry-over — follow-up questions reference what the AI has already seen and discussed
Other improvements
- Gemini Files API integration for more reliable media handling in conversations
- Device location context is now passed to conversations for location-aware responses
- Updated branding from Sen to Camera Search across the application
- Multilingual support with locale management for English and Spanish