OuteTTS
Pure language modeling approach to TTS without traditional audio codecs.
About
OuteTTS is a text-to-speech model that treats speech as a pure language modeling problem, generating audio as next-token prediction without a separate audio codec or vocoder pipeline. It supports voice cloning, stays lightweight, and ships through llama.cpp bindings as well as Transformers, with Python and npm packages. Released as an open model by OuteAI.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- Text-to-Speech (TTS)
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Intermediate (3/5)
- Minimum VRAM
- 4 GB
- Added
- Apr 3, 2026
Related Tools
Lightweight and expressive TTS model with 82M parameters for fast local inference.
Open-source dialogue TTS model by Nari Labs supporting multi-speaker conversations.
Transformer-based text-to-audio model by Suno that generates speech, music, and sound effects.
Multilingual TTS with zero-shot voice cloning and streaming support.
Deep learning TTS library by Mozilla with Tacotron and WaveRNN implementations.
Emotion-controllable TTS engine by NetEase with 2000+ voices.