Voice Library
Browse, preview, and compare 100+ AI voices across 24+ models. Find the perfect voice for your project.
101 voices found
No voices match your filters. Try adjusting your search criteria.
Voices by AI Model
Each TTS model has its own set of voices with unique characteristics. Some models support voice cloning, allowing you to use any voice as a reference.
Bark 28 voices Standard
Try ModelTransformer-based text-to-audio model that generates realistic speech, music, and sound effects.
Chatterbox 1 voices Premium
Try ModelState-of-the-art zero-shot voice cloning with emotion control from Resemble AI.
Default
EnglishCosyVoice 2 5 voices Standard
Try ModelAlibaba's scalable streaming TTS with human-parity naturalness and near-zero latency.
Dia TTS 2 voices Standard
Try ModelMulti-speaker dialog generation model that creates natural conversations between speakers.
GPT-SoVITS 1 voices Standard
Try ModelFew-shot voice cloning TTS that replicates any voice from just 5 seconds of audio.
Default
ChineseIndexTTS-2 1 voices Standard
Try ModelZero-shot TTS with fine-grained emotion control and high expressiveness.
Default
EnglishKokoro 26 voices Free
Try ModelLightweight 82M parameter model delivering studio-quality speech with blazing-fast inference.
MeloTTS 7 voices Free
Try ModelHigh-quality multilingual text-to-speech that runs on CPU with minimal latency.
OpenVoice 1 voices Premium
Try ModelInstant voice cloning with granular control over style, emotion, and accent.
Default
EnglishOrpheus 8 voices Standard
Try ModelHuman-level emotional TTS model trained on 100K hours of speech data.
Parler TTS 1 voices Standard
Try ModelDescribe the voice you want in natural language and Parler generates matching speech.
Default
EnglishPiper 7 voices Free
Try ModelA fast, local neural text to speech system optimized for Raspberry Pi and embedded devices.
Qwen3 TTS 9 voices Standard
Try ModelAlibaba's multilingual TTS with voice cloning, preset voices, and voice design from text.
Spark TTS 1 voices Standard
Try ModelVoice cloning TTS with controllable emotion and speaking style via prompts.
Default
EnglishStyleTTS 2 1 voices Premium
Try ModelHuman-level text-to-speech through style diffusion and adversarial training.
Default
EnglishTortoise TTS 1 voices Premium
Try ModelMulti-voice text-to-speech focused on quality with autoregressive architecture.
Random
EnglishUnderstanding AI Voices
Voice Quality Tiers
TTS.ai offers voices across three quality tiers. Free-tier voices from Piper, VITS, and MeloTTS deliver fast, good-quality synthesis at no cost. Standard-tier voices from models like Kokoro and CosyVoice 2 offer more natural prosody and emotion. Premium-tier voices from OpenVoice, Chatterbox, and StyleTTS 2 provide the most realistic, human-like speech available in open-source TTS.
Multilingual Voices
Many voices support multiple languages. Some models like CosyVoice 2 and GPT-SoVITS support cross-lingual synthesis, where a voice trained in one language can speak naturally in another. The language filter above lets you find voices that natively support your target language, ensuring the best pronunciation and intonation.
Voice Cloning
Some models support voice cloning, which means you can use any voice as a reference to create speech that sounds like that person. Upload a short audio sample (10-30 seconds) and the model will adapt to match the voice characteristics. Models that support cloning include GPT-SoVITS, CosyVoice 2, and Chatterbox.
Choosing the Right Voice
The best voice depends on your use case. For audiobooks and podcasts, use premium voices with natural prosody. For game characters, explore diverse voices across models. For accessibility and screen readers, choose clear, well-paced voices. For quick prototyping, free-tier voices offer instant results with no credit cost. Preview each voice with the play button before making your choice.
Frequently Asked Questions
Record, Enhance, and Transform Your Voice
Use the Voice Recorder with our full suite of AI audio tools. Clone your voice, transcribe speech, enhance quality, and more.