kokoro-onnx

A text-to-speech (TTS) project based on Kokoro and ONNX runtime.

CommonProductProgrammingTTSSpeech Synthesis

kokoro-onnx is a text-to-speech (TTS) project based on the Kokoro model and ONNX runtime. It supports English and plans to support French, Japanese, Korean, and Chinese. The model offers near real-time performance on macOS M1 and provides a variety of voice options, including whispering. The model is lightweight, approximately 300MB (around 80MB when quantized). This project is open-source on GitHub under the MIT license, facilitating easy integration and use for developers.

Supports English (soon to support French
Japanese
Korean
and Chinese)
Offers near real-time performance on macOS M1
Provides a variety of voice options
including whispering
Lightweight model
approximately 300MB (around 80MB when quantized)
Based on ONNX runtime

The primary target audience is developers and researchers who can utilize this model to add text-to-speech capabilities to applications or engage in research and development related to speech synthesis. Its open-source nature and lightweight characteristics make it suitable for developers who wish to integrate high-quality TTS functionality into their projects without building a model from scratch.

Add voice prompt functionality to mobile applications
Integrate into smart assistant devices for natural language interactions
Conduct research on speech synthesis to explore new voice generation technologies

1. Install uv (recommended) or use a regular Python environment
2. Create a new project folder and run 'uv init -p 3.12' to initialize the project within it
3. Use 'uv add' to add the kokoro-onnx and soundfile dependencies
4. Copy the contents of examples/save.py into hello.py
5. Download kokoro-v0_19.onnx and voices.json files and place them in the project directory

Visit

kokoro-onnx Visit Over Time

Monthly Visits

490881889

Bounce Rate

37.92%

Page per Visit

5.6

Visit Duration

00:06:18

kokoro-onnx Visit Trend

kokoro-onnx Visit Geography

kokoro-onnx Traffic Sources

kokoro-onnx Alternatives

audiblez — A tool to convert eBooks into audiobooks.

Productivity•eBooks•audiobooks

Zasper — A super IDE designed for data science, supporting large-scale concurrent processing.

InternationalSelection•Data Science•IDE

174

Mini-Omni — An open-source multimodal large language model that supports real-time voice input and streaming audio output.

Productivity•Multimodal•Speech Recognition

516

speech-to-speech — Open-source speech-to-speech conversion module

Programming•Speech Recognition•Natural Language Processing

576

FunAudioLLM — Foundation model for natural voice interaction understanding and generation

Others•Speech Recognition•Speech Synthesis

588

Hailuo AI Audio — Hailuo AI Audio is an audio synthesis tool designed to create realistic speech.

Video•Speech synthesis•Audio production

OpenLIT — OpenLIT is an open-source platform for the observability of GenAI and LLM applications.

InternationalSelection•Open Source•Performance Optimization

RealtimeSTT — A robust, efficient, and low-latency speech-to-text library equipped with advanced voice activity detection, wake word activation, and instantaneous transcription features.

Productivity•Speech Recognition•Real-time Transcription

self-adaptive-llms — A real-time adaptive framework for unseen tasks using large language models.

Programming•Artificial Intelligence•Large Language Models

InternLM3-8B-Instruct — InternLM3-8B-Instruct is an open-source instruction model with 8 billion parameters designed for general-purpose use and advanced reasoning.

Programming•Large Language Model•Open Source

Ollama OCR for Web — A powerful OCR package that utilizes advanced visual language models to extract text from images.

Image•OCR•Image Recognition

108

DocWrangler — An open-source interactive development environment for building and optimizing LLM-based data processing pipelines.

Productivity•LLM•Data Processing

21st — An npm for design engineers: The largest marketplace for React Tailwind components, modules, and hooks based on shadcn/ui.

Design•React•UI Components

Ingredients — A project that combines custom photos with video using a video diffusion transformer.

Video•Video Creation•Customization

Kokoro-82M — A cutting-edge text-to-speech (TTS) model with 82 million parameters.

Music•Text-to-Speech•Speech Synthesis

702

Wren AI — An open-source SQL AI agent that simplifies the conversion of text to SQL.

Productivity•Data Access•SQL Generation

Amurex — Amurex is an AI meeting assistant tool that offers real-time suggestions, meeting notes, and summary highlights.

Productivity•Meeting Assistance•Real-Time Suggestions

138

fixa — AI Voice Agent Testing and Observability Platform

Business•Voice Agents•Testing

114

Llama-3-Patronus-Lynx-70B-Instruct — An open-source evaluation model for detecting hallucinations, based on the Llama-3 architecture with 70 billion parameters.

Programming•Hallucination Detection•Language Model

Bakery — An open-source platform for AI model fine-tuning and monetization, empowering AI startups, machine learning engineers, and researchers.

Programming•Model Fine-tuning•Monetization

Open Deep Research — An open-source alternative that generates AI reports based on search results

Productivity•Report Generation•Search

156

Epigram — An open-source, free, and AI-driven news aggregation platform that provides concise news summaries.

Others•News•Open Source

138

vectrix-graphs — A graphical library for multi-model embeddings, supporting visualization of various models and data types.

Programming•Graph Library•Multi-Model Embedding

VITA-1.5 — VITA-1.5: A GPT-4o level multimodal large language model for real-time visual and speech interaction.

Programming•Multimodal•Large Language Model

180

Dotomo — An entertaining reminder app that helps users tidy their rooms.

Entertainment•Organization•Reminders

opensource_notebooklm — An open source implementation of NotebookLM using Deepseek-V3 and PlayHT TTS technologies.

Programming•Open Source•AI Dialogue

168

PRIME-RL — PRIME enhances the reasoning abilities of language models through implicit reward-driven online reinforcement learning.

Programming•Reinforcement Learning•Reasoning Capability

GitDiagram — Convert any GitHub repository into an interactive chart for project visualization.

Programming•GitHub•Project Visualization

TangoFlux — An efficient text-to-audio generation model

Music•Text-to-audio•Audio generation

114

Best AI Websites & Tools