Say it. GAIA handles the rest.
Activate voice mode and have a real-time conversation — Deepgram transcribes, GAIA responds with ElevenLabs TTS, and all the same tools are available hands-free.
Multi-Platform
Key capabilities
What makes Voice powerful.
Sub-second STT
Deepgram delivers near-instant transcription so GAIA hears you as you speak.
Natural TTS
ElevenLabs generates expressive, natural speech for every GAIA response.
Full tool access
Voice mode has all the same capabilities as chat: todos, email, research, calendar, workflows.
How it works
Three steps to get started.
Set up in minutes. Works automatically from there.
Activate voice mode in the app
Tap the microphone button in chat to start a real-time voice session.
Speak and GAIA listens
Deepgram transcribes your speech in near real time and sends the text to GAIA's agent.
GAIA responds and reads it aloud
The agent completes actions and ElevenLabs TTS speaks the response back through your speaker.
Use cases
How teams use this.
Real workflows, real outcomes.
Hands-free task creation while commuting
A founder commutes by train and dictates tasks to GAIA hands-free — GAIA creates them with the right project and priority parsed from the spoken instruction.
Quick email reply without typing
A manager says 'reply to the last email from Sarah and tell her the report is ready' — GAIA drafts and sends without the user touching a keyboard.
Real-time research during a walk
A researcher asks GAIA about a topic while walking, receives a spoken summary, and follows up with clarifying questions — a full research session hands-free.
FAQ
Frequently asked questions.
Everything you need to know.
Related
Features that work well together.
Combine these with Voice for more power.
