OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Local & Self-hosted AI

Browserai

BrowserAI is a TypeScript library for running supported language and audio models directly in a web browser. Its documented examples cover text generation, structured JSON output, speech recognition, text-to-speech and audio source separation, using engines including MLC, Transformers, Flare and Demucs.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Browserai — OpenViST project profile in Local & Self-hosted AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use BrowserAI when an application needs supported model inference in the browser, including text, speech or audio workflows, and a WebGPU-capable browser is available.

Who it is for

  • Web developers adding browser-based model inference to applications
  • Researchers and hobbyists experimenting with local browser inference
  • Builders of AI tools, including agent workflows

Documented uses

  • Generate text or chat responses with a browser-loaded model.
  • Request structured output using a JSON schema.
  • Transcribe recorded audio with a Whisper model.
  • Produce speech from text with Kokoro.
  • Separate audio into stems such as vocals, drums, bass and other.
Before you choose

Requirements & limits

The repository specifies an MIT license. Its setup instructions use npm or Yarn; no account requirement or pricing is stated in the cited documentation.

  • The requirements name a modern browser with WebGPU support, citing Chrome 113+, Edge 113+ or equivalent.
  • Models that require shader-f16 need hardware supporting 16-bit floating-point operations.
  • The README says offline use is possible after the initial model download.
  • The repository lists multiple engines and model families; confirm that the intended model is among the supported options before designing around it.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up BrowserAI for text generation

Install the package, load a listed model and generate a text response in a browser application.

Before you start

  • npm or Yarn
  • A modern browser with WebGPU support (Chrome 113+, Edge 113+ or equivalent)
  • For models requiring shader-f16, hardware supporting 16-bit floating-point operations

Steps

  1. Install @browserai/browserai with npm or Yarn.

  2. Import BrowserAI and create an instance.

  3. Load a listed model, such as llama-3.2-1b-instruct.

  4. Call generateText with a prompt and read the returned message content.

Expected outcome

The example returns generated text from the loaded browser model.

Guide limitations

  • This is a source-based setup recipe, not a compatibility or execution test.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
12 October 2026
Original website title
sauravpanda/BrowserAI · Official homepage title · retained in its source language
How we review sourcesSuggest a correction

Related options

Browseragent.dev — A separate no-code AI agent builder identified by the BrowserAI repository as powered by BrowserAI.