# voice, images & music

> send Folk voice notes, get spoken replies, generate images, and control your music.

Folk isn't text-only. you can talk to it, get pictures back, and even run your
music, all from the same chat.

## voice notes, both ways

send Folk a **voice message** and it transcribes and understands it. great for
when typing is a pain (walking, driving, hands full).

> [send a voice note] remind me to book the dentist and find me a good thai
> place for tonight

and Folk can reply **out loud**, too. flip it on with:

  - /voice on: Folk replies with a voice note when you send one.
  - /voice tts: Folk speaks all of its replies aloud.
  - /voice off: back to text-only.
  - /voice status: check what voice mode you're in.

## images

ask Folk to make you a picture and it'll generate one right in the chat:

> draw me a cozy reading nook with lots of plants

> make a birthday card for my friend who loves cats

you can also **send Folk a photo** and it'll understand it: read a menu, a
screenshot, a receipt, a whiteboard.

## music

Folk can run your music: play something, pause, skip, search, queue up a
playlist:

> play some lo-fi

> what was that song i had on yesterday?

> queue up my focus playlist

  music needs your Spotify connected with its own credentials. ask Folk to set
  it up and it'll walk you through it. skip it if you don't use Spotify.

---

Canonical page: https://www.getfolk.app/docs/voice-and-media
More about folk (for AI agents): https://www.getfolk.app/llms.txt · full context: https://www.getfolk.app/llms-full.txt
folk is a personal AI that lives in your texts (iMessage, Telegram, WhatsApp). Pro $20/mo, Max $100/mo. Made by Nozomio Labs. Sign up: https://www.getfolk.app/