An ultra-lightweight AI model under 25 MB for text-to-speech (TTS). Generate high-quality voices directly in your browser, without a GPU. Fast, free, and open source

An open-source project for high-quality text-to-speech. Explore a fast, high-performance voice generator. Possibility of cloning a voice with great precision

A free plugin available on ChatGPT-4 that can read any text you submit to it

An ultra-fast, open-source text-to-speech model that transforms your texts into natural speech (82M parameters only). Create British or American English voices in 10 different styles

Integrate AI-generated voices into your applications: fast, accurate and scalable transcription via an easy-to-use API

Discover Qwen-TTS, Alibaba's AI text-to-speech model. Enjoy natural, expressive speech, multilingual (EN/ZH) with dialects. Also available via the Qwen API

A voice generator with over 700 voices and 90 different languages

An open-source TTS model created by Microsoft AI to generate expressive, long audio conversations with multiple speakers. Ideal for podcasts and dialogues

An application that converts your documents into podcasts hosted by two AI presenters. Listen to your articles, books and PDFs as natural conversations in 32 languages

A tool that transcribes voices into text in real time

AI-driven software turns any text into a realistic human voice

Converts your text into a human and fairly natural voice