Explore 25+ of the best TTS models across open-source and commercial platforms
A lightweight, fast TTS model built on LLaMA.
A 1.6B parameter TTS model from Nari Labs.
An 82M parameter TTS model by Hexgrad.
A 1B parameter open-source TTS model from Sesame.
Comes in 3B/1B/400M/150M variants by Canopy Labs.
Multilingual voice cloning with only 6 seconds of audio.
Trained on 300K hours, supports English, Chinese, Japanese.
Conversational TTS with detailed prosody control.
Advanced control over pitch, speed, and emotion.
High-quality multilingual speech with emotional nuance.
Expressive speech generation with complex prosody.
Zero-shot voice cloning across multiple languages.
A high-quality TTS engine with multi-language support.
Lightweight TTS with wide language coverage.
University of Edinburgh's TTS engine.
Ultra-realistic voices with emotion and multilingual support.
Simple and powerful voiceovers in 20+ languages.
Large voice library and exportable TTS.
Enterprise-grade voice studio and API.
Lifelike voice transformation for creative projects.
Natural-sounding reading companion.
AI voice generator and podcast host.
Long-standing TTS for personal and professional use.
Create videos with TTS and stock media.
AI avatars with expressive voice options.
Expressive AI voice actors for stories.
Adjust pitch, speed, and effects in TTS.
Powerful editor with built-in TTS.
AWS TTS with 60+ voices and languages.