@polyweave/minimax (1.0.2)
Published 2026-07-17 15:48:27 +00:00 by Dvorak
Installation
@polyweave:registry=https://hub.kl1.tenere.ai/api/packages/Polyweave/npm/npm install @polyweave/minimax@1.0.2"@polyweave/minimax": "1.0.2"About this package
@polyweave/minimax
MiniMax adapter for Polyweave - multi-modal AI adapter supporting text, audio (TTS with HTTP and WebSocket streaming), image, video, music, voice clone, voice design, and voice management via MiniMax API.
Synopsis
import { createMinimaxAdapter } from '@polyweave/minimax';
const adapter = createMinimaxAdapter({ apiKey: 'YOUR_API_KEY' });
adapter.source.pipe(someSink);
adapter.sink.write({ type: 'PARAM', content: { key: 'model', value: 'MiniMax-M2.1-lightning' } });
adapter.sink.write({ type: 'TEXT', content: { text: 'Hello!' } });
Install
npm install @polyweave/minimax
API
createMinimaxAdapter(config)
Returns an IFrameDuplex stream adapter. Configuration options:
| Option | Type | Default | Description |
|---|---|---|---|
apiKey |
string | process.env.MINIMAX_API_KEY |
MiniMax API key |
baseURL |
string | auto (region-based) | API base URL |
region |
string | 'international' |
'international' or 'china' |
timeout |
number | 60000 |
Request timeout in ms |
maxRetries |
number | 2 |
Max retry count |
Frame Types
- Input:
TEXT,AUDIO,IMAGE,VIDEO,TOOL_RESULT,PARAM,COST_CHECK,START,END - Output:
TEXT,AUDIO,IMAGE,VIDEO,TOOL_CALL,RECEIPT,ERROR,COST,END
Tasks
Route via task PARAM: tts, image, video, music, voice_clone, voice_design, voice_management, delete_voice. Default: text generation via Anthropic-compatible endpoint.
Tests
npm test
Requirements
- Node.js >= 18.0.0
@polyweave/core(peer)@polyweave/errors(peer)
License
MIT
Dependencies
Dependencies
| ID | Version |
|---|---|
| @polyweave/push-websocket | * |
Development Dependencies
| ID | Version |
|---|---|
| @rigor/core | * |
Peer Dependencies
| ID | Version |
|---|---|
| @polyweave/core | * |
| @polyweave/costs | * |
| @polyweave/errors | * |
Keywords
polyweave
minimax
tts
ai
adapter