WebInfer

🐍

Python Inference

Local audio generation via Python inference engine (Stable Audio Open)

Free
Audio & Speech
Local

Configure Python Inference

Enable Python Inference in Settings

Go to Settings
About Python Inference

Run powerful Python-based AI models locally through the WebInfer Python Inference Engine. Currently supports Stable Audio Open 1.0 for generating up to 47 seconds of high-quality stereo audio. Requires running the Python server separately.

Key Features
  • Stable Audio Open 1.0 for audio generation
  • Up to 47 seconds of stereo audio at 44.1kHz
  • CUDA, MPS (Apple Silicon), and CPU support
  • Automatic GPU memory optimization
  • No API keys required
  • Fully local - no data leaves your machine
Capabilities
audio-generation
local
Configuration Schema
Required and optional fields for configuring this provider
FieldTypeRequired
baseUrl
url
Optional
CLI Usage
For users running the daemon server locally or a self-hosted gateway

Add provider:

npx webinfer provider add python-inference

Test connection:

npx webinfer provider test python-inference
Programmatic Usage
Use Python Inference in your code with WebInfer

Basic usage:

import { generateText } from "webinfer"

// WebInfer automatically routes to the best available provider
const result = await generateText({
  prompt: "Write a haiku about programming"
})

console.log(result.text)

Specify Python Inference explicitly:

import { generateText } from "webinfer"

const result = await generateText({
  prompt: "Write a haiku about programming",
  provider: "python-inference"
})

console.log(result.text)
console.log("Provider:", result.provider)
console.log("Model:", result.model)

Streaming:

import { streamText } from "webinfer"

const { textStream } = await streamText({
  prompt: "Write a story about AI",
  provider: "python-inference"
})

for await (const chunk of textStream) {
  process.stdout.write(chunk)
}
Pricing
Free
Completely free. All computation happens locally on your device.