DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to ship a browser voice with no WebGPU or download with Paradee

Use Paradee's browser phonemizer and ONNX file to speak text inside a web page.

Short answer: Clone the repo with git clone https://github.com/sahilmahendrakar/paradee and open the web/ folder; then use web/misaki.js to convert text to misaki-style phonemes, because browser phonemizers such as kokoro-js write some sounds differently; load the ONNX file from the Hugging Face model page into a browser ONNX runtime and pass phoneme ids as input_ids with speed set to 1.0. All steps.

Who it is forA front-end developer building a Chrome extension or web app that needs speech but cannot require WebGPU or a large model download.

The problemMost in-browser TTS needs WebGPU or a big download, which rules out many users and pages.

The outcomeA browser feature that turns text into speech using the light Paradee model, following the same setup as the Chickadee extension.

What you need first

  • Python with pip installed
  • Internet access for the first run, to download the 8.5 MB model and misaki's English dictionary data
  • Audio output support (soundfile is used in the README example)

Steps

  1. Clone the repo with git clone https://github.com/sahilmahendrakar/paradee and open the web/ folder. (inferred, check the README)
  2. Use web/misaki.js to convert text to misaki-style phonemes, because browser phonemizers such as kokoro-js write some sounds differently.
  3. Load the ONNX file from the Hugging Face model page into a browser ONNX runtime and pass phoneme ids as input_ids with speed set to 1.0. (inferred, check the README)
  4. Read the waveform output, which is float32 at 24 kHz, and play it with the Web Audio API.

Prompt for your agent

Clone sahilmahendrakar/paradee, read web/misaki.js and the ONNX input spec in the README, then write a minimal browser page that speaks the text <your text>. Expect audio playback at 24 kHz with no WebGPU. Verify that the phoneme ids start and end with pad token 0 and total at most 512 before running inference.

Caveat. The README does not give a browser runtime or loading code, so the ONNX loading step is an inference and the author's Chickadee extension is the only documented browser use.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for sahilmahendrakar/paradee and "Ship a browser voice with no WebGPU or download"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer