--- license: apache-2.0 library_name: transformers.js language: - en base_model: - hexgrad/Kokoro-82M pipeline_tag: text-to-speech --- # Kokoro TTS Kokoro is a frontier TTS model for its size of 82 million parameters (text in/audio out). These ONNX models have been exported from the original [Hugging Face](https://huggingface.co/hexgrad/Kokoro-82M) model via the [kokoro-onnx](https://github.com/adrianlyjak/kokoro-onnx-export) scripts. ## Table of contents - [Usage](#usage) - [JavaScript](#javascript) - [Python](#python) - [Voices/Samples](#voicessamples) - [Quantizations](#quantizations) ## Usage ### JavaScript First, install the `kokoro-js` library from [NPM](https://npmjs.com/package/kokoro-js) using: ```bash npm i kokoro-js ``` You can then generate speech as follows: ```js import { KokoroTTS } from "kokoro-js"; const model_id = "adrianlyjak/kokoro-onnx"; const tts = await KokoroTTS.from_pretrained(model_id, { dtype: "q8", // Options: "fp32", "fp16", "q8", "q4", "q4f16" }); const text = "Life is like a box of chocolates. You never know what you're gonna get."; const audio = await tts.generate(text, { // Use `tts.list_voices()` to list all available voices voice: "af_heart", }); audio.save("audio.wav"); ``` ### Python ```python import os import numpy as np from onnxruntime import InferenceSession # You can generate token ids as follows: # 1. Convert input text to phonemes using https://github.com/hexgrad/misaki # 2. Map phonemes to ids using https://huggingface.co/hexgrad/Kokoro-82M/blob/785407d1adfa7ae8fbef8ffd85f34ca127da3039/config.json#L34-L148 tokens = [50, 157, 43, 135, 16, 53, 135, 46, 16, 43, 102, 16, 56, 156, 57, 135, 6, 16, 102, 62, 61, 16, 70, 56, 16, 138, 56, 156, 72, 56, 61, 85, 123, 83, 44, 83, 54, 16, 53, 65, 156, 86, 61, 62, 131, 83, 56, 4, 16, 54, 156, 43, 102, 53, 16, 156, 72, 61, 53, 102, 112, 16, 70, 56, 16, 138, 56, 44, 156, 76, 158, 123, 56, 16, 62, 131, 156, 43, 102, 54, 46, 16, 102, 48, 16, 81, 47, 102, 54, 16, 54, 156, 51, 158, 46, 16, 70, 16, 92, 156, 135, 46, 16, 54, 156, 43, 102, 48, 4, 16, 81, 47, 102, 16, 50, 156, 72, 64, 83, 56, 62, 16, 156, 51, 158, 64, 83, 56, 16, 44, 157, 102, 56, 16, 44, 156, 76, 158, 123, 56, 4] # Context length is 512, but leave room for the pad token 0 at the start & end assert len(tokens) <= 510, len(tokens) # Style vector based on len(tokens), ref_s has shape (1, 256) voices = np.fromfile('./voices/af_heart.bin', dtype=np.float32).reshape(-1, 1, 256) ref_s = voices[len(tokens)] # Add the pad ids, and reshape tokens, should now have shape (1, <=512) tokens = [[0, *tokens, 0]] model_name = 'model.onnx' # Options: model.onnx, model_fp16.onnx, model_quantized.onnx, model_q8f16.onnx, model_uint8.onnx, model_uint8f16.onnx, model_q4.onnx, model_q4f16.onnx sess = InferenceSession(os.path.join('onnx', model_name)) audio = sess.run(None, dict( input_ids=tokens, style=ref_s, speed=np.ones(1, dtype=np.float32), ))[0] ``` Optionally, save the audio to a file: ```py import scipy.io.wavfile as wavfile wavfile.write('audio.wav', 24000, audio[0]) ```