Skip to main content

​
Top support answers

  • How does the API work: create API key -> call POST /v1/response with character + messages -> reuse session_id.
  • Where to set system instructions: Dashboard -> Bot -> AI Engine -> Behavior (systemInstructions, max 8000 chars).
  • Plan limits: Free 50/4096, Plus 75/8192, Pro 100/16384, Ultra 150/32768 (context/max tokens).
  • Full tier matrix (verbs/msg-min/context/max-tokens): Free 5/20/50/4096, Plus 10/40/75/8192, Pro 20/100/100/16384, Ultra 40/unlimited/150/32768.

​
Product basics

Yes. Private verbs are only accessible by the owner. Public verbs can be discovered and used by others.
Credits cover model inference and processing. Longer context and larger outputs consume more.
Yes. Use Verba app chat, the shared WhatsApp module, or a connected Telegram bot. Pro and Ultra accounts can also use the public API at api.verba.ink.
Yes. Public API access is available on Pro and Ultra plans.

​
Discord FAQ

In server channels, the bot replies when mentioned, when channel is marked AI-enabled, or when a training keyword rule triggers.
Use /activate-channel in that channel.
Use /remove-channel.
Yes. The cleanest setup is to mention both bots in the same channel or enable autonomous mode on both so they can keep the exchange going.
Yes, through Discord Expression Controls. Those controls are enabled by default, but Discord permissions in that channel still matter.
The bot can only create native Discord polls in channels where it has poll permission. If polls are disabled or the channel blocks them, it falls back to a normal text reply.
No. Ultra bots can also join voice chat from a clear normal message asking them to join VC/call.
Server reset requires admin/server-owner/bot-owner permission.
Verba monitors privileged actions by the bot account. Unexplained admin or moderation actions trigger fail-closed containment and the bot leaves the affected server; lower-risk messages/reactions are removed where possible. Rotate any exposed token immediately.

​
WhatsApp and Telegram FAQ

No. The shared gateway’s linked-device state persists across normal server restarts. Relink only after logout, device revocation, or session invalidation.
Create a bot with @BotFather, paste its token in the Telegram module, and add it to a group or open its DM. Verba validates the token, sets a secure webhook, and registers its commands.
Mention it, reply to one of its messages, or have a group admin run /activate_channel.

​
Streaming and social-state FAQ

No. The AI Engine toggle controls edit-in-place replies on Discord, WhatsApp, and Telegram. Ultra-only streaming refers to public API SSE with stream: true.
No. It is a temporary mood layer. Auto mode can consider important memories, but saved personality, facts, system instructions, and safety remain authoritative.

​
Memory and knowledge FAQ

Memory is compact persistent facts; knowledge entries are richer structured references/lore.
Up to 50 entries.
Yes, with Auto Memory enabled and instructions configured.
It does not write on every turn. It waits for enough recent conversation, skips temporary or duplicate facts, and only sometimes attempts a memory. At 50 automatic entries it rolls out the oldest automatic entry instead of freezing; manual entries are preserved.
Improve knowledge entry quality (clear title/category/content), reduce ambiguity, and add training examples for recurring question patterns.

​
API FAQ

Create an API key, call POST /v1/response for text (or POST /v1/image for images), and reuse session_id for follow-up context.
Use Authorization: Bearer vka_... or x-api-key.
Reuse session_id to preserve context for the same caller + character.
Yes with stream: true on /v1/response if the API key owner is on Ultra.
No. Character system/personality is applied automatically.
Max 60 messages, max 4000 chars per message, max 20000 total chars, max 4 image URLs, and max 128 chars for session_id.
Up to 3 active API keys per account.

​
Plans and premium FAQ

Streaming is available on Ultra. Free, Plus, and Pro streaming requests are rejected.
Free: 5, Plus: 10, Pro: 20, Ultra: 40.
Yes. Plan tier sets max model context and max response tokens.
See the Plans and limits guide for complete tier-by-tier details.

​
Account and security FAQ

Up to 3 active keys per account by default.
Yes. You can disable it from settings after verification.
Not while an active paid Patreon subscription is still linked.

Troubleshooting

Fix connection, timeout, and no-response issues.

Question Bank

Larger question-driven reference generated from backend/frontend behavior.

Telegram Module

Connect Telegram and understand its commands and group routing.

Response Streaming

Compare platform streaming with public API SSE.

Plans and limits

Premium tiers, usage limits, streaming, and allowances.