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

How to call the Paradee ONNX graph from any runtime with Paradee

Feed phoneme ids and speed into the ONNX graph and get 24 kHz audio back.

Short answer: Download the int8 ONNX model from huggingface.co/sahilmahendrakar/Paradee-8M-v1.1; then Get the phoneme vocabulary from config.json on the Hub, and build input_ids as int64 [1, T] with a 0 pad token at each end, at most 512 tokens; create speed as float32 [1], where 1.0 is normal speed. All steps.

Who it is forA backend or ML engineer who wants to serve TTS from a non-Python stack or a CPU server, using the raw model file.

The problemWrapping the Python package is awkward in some services, so a direct ONNX interface is needed.

The outcomeA service that takes phoneme ids and returns a float32 waveform at 24 kHz from the single ONNX graph.

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. Download the int8 ONNX model from huggingface.co/sahilmahendrakar/Paradee-8M-v1.1.
  2. Get the phoneme vocabulary from config.json on the Hub, and build input_ids as int64 [1, T] with a 0 pad token at each end, at most 512 tokens.
  3. Create speed as float32 [1], where 1.0 is normal speed.
  4. Run the graph and read the waveform output, float32 [1, samples] at 24 kHz.

Prompt for your agent

Load the Paradee 1.1 int8 ONNX file from sahilmahendrakar/Paradee-8M-v1.1 with an ONNX runtime, build input_ids from phonemes in config.json with 0 pads, and run inference on the text <your phonemes>. Expect a float32 waveform at 24 kHz. Verify the output shape is [1, samples] and that the sample count is greater than zero.

Caveat. The phonemes must come from misaki or be converted to misaki's spelling, since the model was trained only on misaki output and browser phonemizers can cut word accuracy sharply.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for sahilmahendrakar/paradee and "Call the Paradee ONNX graph from any runtime"

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