Bark by Suno
Transformer-based text-to-audio model generating speech, music, and sound effects. Supports multiple languages with emotional expression and realistic voice synthesis.
DramaBox TTS Pinokio is a free, open-source, 1-click local launcher for Resemble AI's DramaBox - a prompt-driven expressive text-to-speech model with voice cloning, built on LTX-2.3. A powerful self-hosted alternative to ElevenLabs.
DramaBox TTS is an open-source expressive text-to-speech and voice cloning model from Resemble AI, packaged for one-click local install through Pinokio. It runs on your own machine, needs no account and no subscription, and produces speech with genuine emotional range rather than the flat delivery most free TTS tools give you.
The commercial voice-cloning tools charge monthly and send your audio to their servers. DramaBox runs locally, so your voice samples never leave your machine, and there is no per-character billing. For podcasters, game developers and content creators, that combination is unusual.
Install Pinokio, then install DramaBox TTS from the Pinokio app store. Pinokio handles the Python environment, model download and dependencies. There is a companion Pinokio wrapper that automates the whole thing.
We wrote a detailed walkthrough covering what it does, how the voice cloning performs, the hardware requirements, and where it falls short: DramaBox TTS Pinokio: Free Open-Source Expressive Voice Cloning.
Transformer-based text-to-audio model generating speech, music, and sound effects. Supports multiple languages with emotional expression and realistic voice synthesis.