Dia is a 1.6B parameter text to speech model created by Nari Labs. It was pushed to the Hub using the PytorchModelHubMixin integration.

ElevenLabs is described as 'Leverages advanced AI for natural speech, offering applications like podcasts, video voiceovers, with a user-friendly interface and extensive voice library' and is a Text to Speech service in the ai tools & services category. There are more than 50 alternatives to ElevenLabs for a variety of platforms, including Web-based, SaaS, Mac, Windows and Android apps. The best ElevenLabs alternative is Voxtral, which is both free and Open Source. Other great apps like ElevenLabs are VoiceCraft, X to Voice, Voice Engine and Kokoro.
Dia is a 1.6B parameter text to speech model created by Nari Labs. It was pushed to the Hub using the PytorchModelHubMixin integration.

Gesserit is the best place to find tools to speed up video creation using AI, find the best text to speech voices to create awesome voiceovers and videos.

Jimlet is a free offline text-to-speech converter for Windows. It runs locally on your computer, without subscriptions or usage limits, and converts text to clear, natural-sounding speech. You can use an ordinary computer without a dedicated GPU to convert arbitrary amounts of...



Unlock audio magic with our online audio workshop. Create sound effects, remix songs, generate voices, and change voices using AI – all in one place, all for free. Whether you’re a content creator, gamer, or storyteller, our tools enhance your projects with professional sound...




Turn any text into natural AI speech — a free voice AI TTS app that gives you realistic, expressive, human-sounding voices.




A privacy-focused online video editor that processes videos entirely in your browser using FFmpeg and WebAssembly. No uploads, no signups required.

Unlock your creative potential with powerful voice cloning. Replicate any voice with stunning accuracy or convert text to speech with our AI voices.


Make an AI copy of your voice that keeps your tone and accent. Our voice cloning tech lets you create natural-sounding speech for videos and podcasts by reading a short text.

BookFab AudioBook Cloud Enhancer utilizes advanced AI to generate high-fidelity voice clones from minimal audio input. This cloud-based tool clones specific voices to produce natural-sounding speech for any creative project.

15.ai, or 15.dev, is a free non-commercial web application and research project that uses artificial intelligence to generate text-to-speech voices of fictional characters from popular media.
Munsit is a comprehensive Arabic Voice AI suite developed by CNTXT AI in the UAE. It features a next-generation model built from the ground up to capture the richness of the Arabic language, supporting over 25+ dialects including Gulf, Levantine, Egyptian, and North African.




AIWriteBook is an all-in-one AI book creation platform used by 15,700+ authors to go from idea to published book on KDP in hours, not months.
