T

text-to-speech

OpenDub: free, open-source AI video dubbing. Translate a video into 17 languages in the speaker's own cloned voice, timed line by line, with subtitles burned in. Windows, macOS and browser; the video file is never uploaded. https://opendub.app

A self-hosted AI platform: inference, tool use, browser automation, image generation, speech synthesis, transcription, object storage, agentic code execution, and more, behind a single OpenAI-compatible endpoint. One docker-compose up.

Telephony for N-ATLAS: Python SDK

Self-hosted Docker speech API for OpenAI-compatible transcription and text-to-speech, streaming ASR, voice cloning, phoneme recognition, and MCP.

Qwen3-TTS over SSH. Pick a voice, clone a voice, design a voice - all through a YAML config piped via stdin. Models run locally, no API keys, no cloud bullshit.

This project provides a client package and example scripts for python to access the alphaspeech pro ASR APIs.

High-performance Text-to-Speech (TTS) REST API service for the Oremi ecosystem.

https://demsking.gitlab.io/oremi-izwi

Agentic pronunciation analysis and research for identifying, verifying, and explaining difficult English pronunciations before speech synthesis.

A manimgl plugin to add narration.

Give your AI agent a voice. Local speech stack for Apple Silicon: TTS, ASR, forced alignment, voices, daemon, and MCP bridge.

Calculadora con voz, orientado para Linux

🚛✈️An advanced Streamlit dashboard designed as an AI-powered assistant for World Movers Phils Inc. This application leverages Google Gemini for multimodal interactions, enabling users to get information, request quotes, marketing, analyze documents/images, use voice commands, and more, all within a custom-themed interface.

The Python script utilizes the win32com library to interact with the Windows Speech API (SAPI), prompting the user to input text to be spoken aloud. It continuously speaks the input text using the default system text-to-speech engine until the user inputs "-1" to terminate the program.

Simple module that helps you to create aloud report with numeric values.

Python package to normalize text for speech-language models using different libraries.

An easy to use wrapper for the BARK text-to-speech engine

This project contains the code for the talk at the tekom 2019 in Stuttgart for "Introduction to Python for Technical Communicators"