Using voice input and text-to-speech

Anuma supports voice recording for input and text-to-speech for output. Speak your prompts instead of typing, and have responses read aloud with your preferred voice.

Voice mode is rolling out gradually and may not be available on your account yet. If you don’t see the microphone icon or a Voice section in Settings, the feature hasn’t reached you — check What’s new for availability updates. The steps below describe how it works once it’s enabled for you.

Voice input

Step 1: Tap the microphone

In any chat, tap the microphone icon next to the chat input to start recording.

Step 2: Speak your prompt

Speak clearly. Anuma transcribes your voice in real-time.

Step 3: Send

Review the transcription and send your message. Anuma processes it like any typed prompt.

Text-to-speech

Step 1: Open Voice settings

Go to Settings > Voice to configure text-to-speech options.

Step 2: Select a voice

Choose from available voices for spoken responses.

Step 3: Enable TTS

With TTS enabled, Anuma reads responses aloud. You can pause, replay, or skip at any time.

Good to know

Where available, voice input works on both web and mobile.
Transcription is processed in real-time as you speak.
Voice settings are saved in your preferences and sync across devices.

Related articles