PierrunoYT/Kokoro-TTS-Local

A local implementation of the Kokoro Text-to-Speech model, featuring dynamic module loading, automatic dependency management, and a web interface.

What it solves

This project provides a local, easy-to-install implementation of the Kokoro-82M text-to-speech (TTS) model. It eliminates the need for cloud-based TTS services by allowing users to generate high-quality speech on their own hardware, including full offline support after the initial setup.

How it works

It wraps the Kokoro-82M model (an 82-million parameter model) and automates the downloading of model weights and voice files from Hugging Face. Users can interact with the system via a command-line interface (CLI) or a Gradio-based web interface. The system supports multiple output formats (WAV, MP3, AAC) and can utilize CUDA-compatible GPUs for faster audio generation.

Who it’s for

  • Developers and users who want high-quality, local TTS without relying on external APIs.
  • People needing offline speech synthesis for privacy or connectivity reasons.
  • Users looking for a multilingual TTS solution that supports 9 different languages.

Highlights

  • Multilingual Support: Includes 54 voices across 9 languages, including American and British English, Japanese, Mandarin Chinese, Spanish, French, Hindi, Italian, and Brazilian Portuguese.
  • Flexible Interfaces: Offers both an interactive CLI and a web-based UI with "Speed Dial" presets for saving favorite voice and speed combinations.
  • Offline Capability: Full offline mode support via the HF_HUB_OFFLINE environment variable.
  • Cross-Platform: Compatible with Windows, Linux, and macOS, with Docker support for simplified deployment.
  • Comprehensive Diagnostics: Includes a kokoro-tts-check tool to validate Python versions, CUDA availability, and system dependencies.

Related

  • Dispatch
    Kokoro TTS: High-Quality, CPU-Friendly Local Text-to-Speech

    Kokoro is an 82M parameter model that provides high-quality, local text-to-speech synthesis on CPUs, offering an OpenAI-compatible API for easy integration into private AI pipelines.

  • Project
    remsky/Kokoro-FastAPI

    Dockerized FastAPI server that wraps the open‑source Kokoro‑82M TTS model, offering an OpenAI‑compatible speech endpoint, streaming, multilingual voices, voice‑mixing, inline SSML tags, custom voice‑tuning and a web UI. Runs on CPU, NVIDIA/AMD GPUs or Apple Silicon via Docker or uv.

  • Project
    thewh1teagle/kokoro-onnx

    A lightweight ONNX Runtime implementation of Kokoro-TTS that enables fast, multi-language text-to-speech generation on CPU and GPU.

  • Project
    lucasjinreal/Kokoros

    A high-performance Rust implementation of the Kokoro TTS model providing fast text-to-speech synthesis via a CLI, Rust crate, and OpenAI-compatible API server.

  • Project
    kyutai-labs/pocket-tts

    Pocket TTS is a 100 M‑parameter, CPU‑only text‑to‑speech library that streams audio with ~200 ms latency, supports multiple languages and voice cloning, and offers a Python API, CLI, and local HTTP server. It can be installed via pip (or uv) and runs faster than real‑time on modest hardware, with community‑trained models and several alternative runtimes for browsers and embedded devices.