MiniMax for your voice agent
MiniMax is a multimodal AI platform for text, video, speech, image, music, and file workflows. Its unified APIs help developers build rich AI experiences from one service.
Call 1800 570 693 to talk to the demo agent. Plans start at A$49 a month.




Integration record
- Status
- Available
- Plan
- Every plan, from Starter at A$49 a month
- How it connects
- With an API key. You create a key in MiniMax and paste it on a secure page in Connected apps.
- What it reads
- 13 actions, such as count Message Tokens, download File and estimate Responses Input Tokens.
- What it changes
- 17 actions, such as clone Voice, create Async Speech and create Legacy Video.
- What starts an action
- The agent runs an action during a call or chat when the conversation needs it. It only runs the actions you switch on.
- Custom work
- You choose each action from its list of 35. Anything the list doesn't cover needs a custom API tool on Scale, or a Concierge build.
- Checked
- Action list checked 14 November 2026. We haven't tested each action.
MiniMax actions
Reads 13
- Count Message Tokens
- Download File
- Estimate Responses Input Tokens
- Get Account Balance
- Get Async Speech Task
- Get File
- Get Legacy Video Task
- Get Template Video Task
- Get Video Task
- List Files
- List Text Models
- List Video Tasks
- List Voices
Changes 14
- Clone Voice
- Create Async Speech
- Create Legacy Video
- Create Template Video
- Create Video
- Create Video Prompt
- Design Voice
- Generate Image
- Generate Native Chat Completion
- Generate Text
- Regenerate Video
- Synthesize Speech
- Transcribe Audio
- Upload File
Deletes 3
- Delete File
- Cancel or Delete Video Task
- Delete Voice
MiniMax setup
Pasting a MiniMax API key
Create an API key in MiniMax, choose MiniMax in Connected apps and paste the key on the secure page.
Choosing the actions
Choose which of the 35 actions the agent may use. Start with lookups and add the ones that change MiniMax when you're ready.
Testing, then publishing
Watch the agent use the live app in the browser tester, then publish. Voice and text agents share the connection.
More integrations
Get started
Tell us what your callers ring about, and we build and test the agent for you.


