LibreSpark/LibreTTS

TTS-文本转语音/文本转语音前端，兼容OpenAI、EdgeTTS等接口

What it solves

LibreTTS provides a free, web-based interface for converting text to speech (TTS), allowing users to generate audio from text with a wide variety of voice options and customizable settings without needing complex local setups.

How it works

The tool acts as a frontend and API gateway that connects to various TTS engines. It supports the Microsoft Edge TTS API and allows users to add their own custom API endpoints, including those compatible with the OpenAI TTS format (such as LMStudio or LocalAI).

Who it’s for

It is designed for individuals who need a simple way to generate high-quality speech audio from text, as well as developers who want to self-host a TTS gateway with password protection and API access.

Highlights

  • Extensive Voice Library: Supports over 300 voices across different languages and accents.
  • Custom API Integration: Ability to add custom OpenAI-format or Edge-format TTS APIs.
  • Audio Customization: Adjustable speech rate and pitch.
  • Long Text Handling: Automatically segments long text for processing.
  • Deployment Flexibility: Easy deployment via Vercel, Cloudflare Pages, or Docker.
  • UTF-8 History: Maintains a history of up to 50 recent conversions.
  • Responsive Design: Fully compatible with mobile devices.

Related

  • Project
    SonyResearch/Woosh

    A collection of generative models from Sony AI for creating high-quality sound effects via text-to-audio and video-to-audio generation.

  • Project
    jzjzzzzzzz/agent-me

    Agent‑Me is an open‑source FastAPI + React system that turns a personal Markdown knowledge base into an inspectable AI “twin”. It runs a deterministic multi‑stage pipeline (retrieval → planner → researcher → critic → writer → optional verifier) and returns the full execution trace, making every answer evidence‑grounded and auditable. The repo provides Docker‑compose and local‑toolchain setups, optional OpenAI‑compatible LLM integration, a test suite with deterministic fixtures, and a bilingual curriculum for developers who want to extend the architecture.

  • Project
    Socialpranker/deepdive

    Deepdive is an open‑source Claude Code skill that turns a plain research request into a reproducible 13‑phase pipeline. It reframes the question, builds a detailed plan, runs parallel sub‑agents across 29 curated search channels, triangulates and filters evidence, performs adversarial red‑team review, and verifies citations for liveness and faithfulness. The output is a structured folder of markdown files (plan, sources, claims, memo, full report) with every claim linked to its source, making the research auditable and reusable. Installation is a one‑line git clone for Claude Code, and the methodology can be adapted to other LLMs.

  • Project
    kstonekuan/tambourine-voice

    An open-source universal voice-to-text interface that uses AI to transcribe and format speech into clean text, typing it directly into any active application.