Photos and voice notes
Companions don't just reply in text. They send voice notes in their own voice and AI-generated photos that match their personality, mood, and whatever you're talking about. This page covers what to expect, how to ask for media, and the monthly limits on each plan.
Voice notes
Voice notes arrive in the Telegram chat as playable audio bubbles. Tap the play icon to hear the companion speak. Each companion has a distinct voice that matches their personality, so the same line of text from two different companions will sound noticeably different.
Voice notes are sent occasionally rather than on every reply. A companion is more likely to send one when the moment calls for it, such as a longer story, a quiet thought before bed, or a reply that feels more personal than text would carry. You can preview a companion's voice on their profile in the Cloa app before you start chatting.
Photos
Photos are AI-generated in a candid, everyday style — selfies, shots of what the companion is doing, or the scene around them. They reflect the companion's current context in the conversation. If you've been talking about coffee, you might receive a photo from a cafe. If they mention they're at home, the photo will look like home.
Photos are sent occasionally, woven into the flow of the conversation rather than on demand for every message. They are intended to feel like the kind of picture a friend might send, not a stock image library.
Asking for a photo
You can ask for a photo in plain language inside the Telegram chat. Messages like "send me a pic" or "what are you wearing today" are understood as photo requests.
The companion decides whether and when to send one. They may reply with a photo right away, send one later in the conversation, or respond in text if a photo doesn't fit the moment. This mirrors how a real conversation works rather than treating the request as a guaranteed command.
Monthly limits
Photos and voice notes are tracked separately from text chat. Text messages have their own allowance on each plan; the media limits below apply only to generated photos and voice notes received in Telegram.
| Plan | Photos per month | Voice notes per month |
|---|---|---|
| Free | 3 | 4 |
| Plus | 50 | 50 |
| Pro | 500 | 500 |
Limits reset at the start of each billing month. Unused photos and voice notes do not carry over.
When you reach a limit
When you reach the photo or voice note limit for the month, the Telegram conversation continues in text only. The companion will still reply, remember context, and stay in character — only generated media pauses.
You have two ways to continue receiving media before the month resets:
- Wait for the monthly reset, after which the allowance refills.
- Upgrade to a higher plan with a larger media allowance. See Plans and billing for details.
Privacy
AI-generated photos and voice notes exist only inside your Telegram conversation with the companion. They are not posted, shared, or reused outside of that chat, and they are not visible to other Cloa users. The media is generated for your conversation and stays there.
See also
Set up a companion on Telegram
There's basically nothing to set up. Tap Chat on Telegram from any companion's profile and you're talking — no sign-up, no codes, no waiting.
Your companion's memory
Each companion has their own memory. Hana doesn't know what you told Aria, and your main Cloa doesn't see any of it.