For Agents
Create, update, clone, and delete conversational AI characters on Convai for games and interactive experiences. Agents authenticate with a CONVAI-API-KEY header.
Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Convai Character API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with Convai Character API.
Create a new conversational AI character with persona and backstory via /character/create
Update character traits, voice, and knowledge via /character/update
Clone an existing character to spin up variants via /user/clone_character
GET STARTED
Use for: I need to create a new AI NPC for my game, Update the backstory and voice of an existing Convai character, Clone an existing character to test a new persona variant, Retrieve the configuration for character ID abc123
Not supported: Does not run real-time conversation, synthesise voice audio, or render avatars — use for AI character lifecycle management only.
Jentic publishes the only available OpenAPI specification for Convai Character API, keeping it validated and agent-ready. The Convai Character API lets developers create, update, retrieve, clone, and delete AI characters used in interactive experiences such as games, virtual worlds, and immersive training. The five POST endpoints cover the full character lifecycle, with authentication via the CONVAI-API-KEY header. The Character API requires a Professional Plan or above on Convai.
Retrieve character configuration and metadata via /character/get
Delete a character permanently via /character/delete
Patterns agents use Convai Character API for, with concrete tasks.
★ Game NPC Authoring
Create and iterate on AI-driven non-player characters for video games and interactive experiences. POST /character/create defines the persona, backstory, and voice; /character/update tunes responses as designers playtest. Suited to studios building dialogue-rich titles where each NPC needs a distinct personality and the team iterates dozens of times before ship.
Create a Convai character named 'Lyra' with a guarded ranger persona and a calm female voice via /character/create
Virtual Tutor and Trainer Cloning
Build a base AI tutor character once, then clone it via /user/clone_character to spin up subject-specific variants such as physics, history, or language tutors. Each clone inherits the base personality and gets domain-specific knowledge layered on with /character/update. Useful for ed-tech and corporate training teams maintaining a stable of consistent virtual instructors.
Clone the base 'Tutor' character and update the clone with a chemistry knowledge profile and the name 'Chem Coach'
Character Lifecycle Management
Maintain a roster of production AI characters by retrieving current state, updating personality drift over time, and removing characters that have been retired from the experience. /character/get inspects current config and /character/delete removes obsolete entries. Useful for live-service experiences where characters evolve across content updates.
Retrieve the config for character ID abc123, update its voice to a new model, and delete two retired character IDs
Agent-Driven Character Authoring via Jentic
An AI agent designs and iterates Convai characters through Jentic without holding the API key. The agent searches Jentic for the create or update intent, loads the schema, and executes the POST call with persona inputs. Through Jentic the CONVAI-API-KEY header is injected from the vault so the agent can run authoring loops without secret exposure.
Search Jentic for 'create a Convai character', load the schema, then create a character with a generated persona and report back the character ID
5 endpoints — jentic publishes the only available openapi specification for convai character api, keeping it validated and agent-ready.
METHOD
PATH
DESCRIPTION
/character/create
Create a new AI character
/character/update
Update an existing character
/character/get
Retrieve character details
/user/clone_character
Clone an existing character
/character/delete
Delete a character
/character/create
Create a new AI character
/character/update
Update an existing character
/character/get
Retrieve character details
/user/clone_character
Clone an existing character
/character/delete
Delete a character
Three things that make agents converge on Jentic-routed access.
Credential isolation
Convai CONVAI-API-KEY values are stored encrypted in the Jentic vault. Agents receive scoped access at execution time and the key is injected into the request header — the raw key never enters the agent's prompt context.
Intent-based discovery
Agents search Jentic by intent (e.g., 'create a Convai character') and Jentic returns the matching POST /character/create or /user/clone_character operation with its input schema.
Time to first call
Direct Convai integration: half a day for header auth, character schema, and clone flow. Through Jentic: under 30 minutes — search, load, execute.
Alternatives and complements available in the Jentic catalogue.
Specific to using Convai Character API through Jentic.
Why is there no official OpenAPI spec for Convai Character API?
Convai does not publish an OpenAPI specification. Jentic generates and maintains this spec so that AI agents and developers can call Convai Character API via structured tooling. It is validated against the live API and kept up to date. Get started at https://app.jentic.com/sign-up.
What authentication does the Convai Character API use?
The API uses an apiKey scheme. Send your key in the CONVAI-API-KEY request header on every call. Through Jentic the key is held in the vault and injected at execution time so it never enters the agent's context window.
Can I clone an AI character with the Convai Character API?
Yes. POST /user/clone_character duplicates an existing character so you can branch a base persona into variants. Use /character/update afterwards to layer domain-specific traits, voice, or knowledge onto the clone.
Do I need a paid plan to use the Convai Character API?
Yes. The Character API requires a Convai Professional Plan or above. The five lifecycle endpoints are gated behind plan-level access — confirm your account tier before integrating.
What are the rate limits for the Convai Character API?
Rate limits are not declared in the OpenAPI spec. Treat the lifecycle endpoints as soft-limited per CONVAI-API-KEY and back off on HTTP 429 responses. Contact Convai support for documented limits on your plan.
How do I create a Convai character through Jentic?
Run jentic search for 'create a Convai character', load the returned POST /character/create operation, then execute it with your persona, backstory, and voice settings. Jentic injects the CONVAI-API-KEY from the vault and returns the new character ID as a structured result.