Voice and calls

Talk to your bots instead of typing, have them read replies aloud, or call them.

Set up a voice provider

Open Settings → Voice, pick a Provider and add its API key:

• ElevenLabs, OpenAI and Fish Audio can speak and transcribe.
• Cartesia speaks only.
• Self-hosted uses your own OpenAI-compatible speech server, such as Kokoro or Whisper. Enter its Server URL.
• macOS uses the voices installed on the Mac running your server, with no key. It appears only when the server runs on a Mac.

Then choose a Voice, and use Hear a sample to check it. Speech model and Transcription model let you pick the provider’s models.

Voice settings apply to every space. A space can customize them in its settings.

Talk instead of typing

Hold the microphone in the composer and speak; release to send. Slide up to lock recording so you don’t have to keep holding.

Hear replies

• To hear one reply, choose Speak this reply on the message.
• To hear every reply from a bot, open its settings, expand Advanced, and turn on Read replies aloud. The Voice next to it overrides your default voice for that bot.

Call a bot

Choose Call at the top of the chat to talk with the bot in real time. During a call you can Mute, open the Transcript, minimize the call and keep using the app, or Hang up. The transcript stays in the chat afterwards.

Bots can call you too: ask “call me at 5 to go over the day”, or a bot may call when you’ve missed the same reminder several times. You’ll see that the bot is calling you; answer or Decline. A missed call shows Call back in the chat.

On mobile

The mobile app uses your phone’s own speech recognition and voices for calls. Pick a Device voice in a bot’s settings. On Android, a call keeps going with the screen off.