Gemini read aloud: listen to answers and change the voice
Google Gemini can read its answers aloud, which is handy for long explanations, recipes or study notes. Many people cannot find where to change the voice, though, especially on a computer.
This guide explains, according to Google’s Gemini help, how to listen to a response, where Gemini’s voice is changed and why it is not in the web settings, and how to keep an answer as an audio file in a voice you choose.
Make Gemini read an answer aloud
Next to a Gemini response, tap Listen and Gemini reads it aloud. Google’s help describes Listen as one of the features where Gemini speaks, along with the Gemini Live voice conversation. Listen reads the response itself; the microphone in the input box is for dictating your prompt.
Change Gemini’s voice
According to Google, Gemini’s voice applies across all Gemini Apps, but for now the setting is only in the Gemini mobile app. Open the app, tap Menu, then your profile picture or initial, then Settings, and tap Gemini’s Voice. Tap a voice name to hear it and tap Confirm. The chosen voice is used in Gemini Live and when Gemini reads responses aloud, also on the web.
Language limits
Google says the number of voices varies across languages, and the option to change Gemini’s voice is not available in some languages. You also need to be signed in to Gemini Apps to change it.
Save an answer as an MP3
Google’s help describes listening to answers, not saving them as files. To keep an answer for a walk, a commute or a study session, copy it into a text file and voice it with the free SuperClonica engine: install it with python -m pip install superclonica-cpu and run superclonica --text-file answer.txt --voice F2 --lang en --normalize --output answer.mp3. It runs offline on an ordinary processor, with no character limit, in 31 languages. Try catalog voices free on their pages first: paste 30 to 100 characters, no account needed.
For developers
Gemini’s speech in the app is separate from the Gemini text-to-speech models offered to developers through Google’s API. If you are building an app and compare speech APIs, see our guide to a Gemini TTS alternative, or run the SuperClonica engine on your own server.