T

text-to-speech

Application to read the same book twice ideally in different languages to easy up to learn a new language

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

Unofficial Go client for the ElevenLabs API, generated from the official OpenAPI spec.

Speech Note Linux app. Note taking, reading and translating with offline Speech to Text, Text to Speech and Machine translation

Make every page accessible: a free, open-source reader that turns slides, PDFs, handouts and web pages into high-contrast notes in your own reading profile, read aloud and offline.

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: Node SDK

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

This project provides a client package and example scripts for TypeScript to access the alphaspeech pro ASR stream API.

LittleCode is an open-source AI-powered design canvas that transforms natural language prompts—text, voice, or visual—into full, production-ready front-end code. Accessible to users of any age or skill level, it supports multiple frameworks, real-time previews, collaboration, and AI-driven design intelligence. With advanced features including accessibility tools, UX optimization, gamified learning, VR/AR support, and futuristic experimental capabilities like sentient-style AI and IoT integration, LittleCode enables anyone to see their design concepts come to life. https://roxanneardary.com/littlecode/

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

This is a fully client-side, JavaScript-only Text-to-Speech (TTS) service using eSpeakNG. No server-side bullshit. Just clone this repo into your desired directory, and you're all set.

A PWA that provides a method to access chat like messaging functionality by using Rest API integrations from the Rhea Generative Framework.

The Rhea client app is component within the Rhea Generative Framework.

Originally intended as a way to demonstrate functionality found within the Rhea Generative Framework. The client app was designed to both demonstrate functionality and provide a foundation to build other components such as live chat (embeddable, etc.).

It has evolved over time to include additional functions for demonstration:

Persona management (role activation and management) Speech-to-text and text-to-speech (browser independent, both part of Rhea's Generative Framework server-side components and available for local hosting) STT captures audio for x seconds, transcribes and offers to either continue transcribing, send as a message, or manually edit.

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.

Flite text-to-speech synthesis bindings for Kit