Documentation / Text-to-Speech

Text-to-Speech

Updated April 5, 2026

Text-to-Speech (TTS) lets your AI assistants speak their responses aloud. Powered by Google Cloud TTS neural voices, it uses prepaid credits from your Agentic credit wallet.

Chat Feature Overrides table showing Audio Out TTS toggle per agent
Toggle Text-to-Speech (Audio Out) per agent in Settings → Agents

Enabling TTS

  1. Go to Agent Builder → Settings → Styles
  2. Under Global Chat Settings, enable Text-to-Speech
  3. Click Save Settings

Once enabled, a speaker icon appears in the chat interface. Click it to hear the assistant’s response read aloud.

Per-Agent Overrides

You can enable or disable TTS per assistant in Settings → Agents → Chat Feature Overrides. The Audio Out column controls TTS for each individual assistant.

Voice Input vs Text-to-Speech

  • Voice Input (Audio In) — free, uses browser speech recognition. You speak, the browser transcribes.
  • Text-to-Speech (Audio Out) — uses prepaid credits. The assistant speaks its response aloud via Google Cloud TTS.

Credits

TTS uses your shared Agentic credit wallet (same credits as Image Generation and Vector Store). Check your balance in Settings → Health → Credit Balance. Purchase credits when your balance runs low.

Browse all documentation →