AI Voice Library
Browse, preview, and compare 100+ AI voices across 24+ models. Find the perfect voice for your project.
101 voices found
声音不匹配过滤器。 尝试调整搜索条件 。
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.
Transformer-based text-to-audio model that generates realistic speech, music, and sound effects.
Chatterbox
1 voices
Premium
尝试模型
State-of-the-art zero-shot voice cloning with emotion control from Resemble AI.
Default
English
CosyVoice 2
5 voices
标准标准标准标准
尝试模型
Alibaba's scalable streaming TTS with human-parity naturalness and near-zero latency.
Multi-speaker dialog generation model that creates natural conversations between speakers.
GPT-SoVITS
1 voices
标准标准标准标准
尝试模型
Few-shot voice cloning TTS that replicates any voice from just 5 seconds of audio.
Default
Chinese
IndexTTS-2
1 voices
标准标准标准标准
尝试模型
Zero-shot TTS with fine-grained emotion control and high expressiveness.
Default
EnglishLightweight 82M parameter model delivering studio-quality speech with blazing-fast inference.
High-quality multilingual text-to-speech that runs on CPU with minimal latency.
Instant voice cloning with granular control over style, emotion, and accent.
Default
EnglishHuman-level emotional TTS model trained on 100K hours of speech data.
Parler TTS
1 voices
标准标准标准标准
尝试模型
Describe the voice you want in natural language and Parler generates matching speech.
Default
EnglishA fast, local neural text to speech system optimized for Raspberry Pi and embedded devices.
Alibaba's multilingual TTS with voice cloning, preset voices, and voice design from text.
Voice cloning TTS with controllable emotion and speaking style via prompts.
Default
English
StyleTTS 2
1 voices
Premium
尝试模型
Human-level text-to-speech through style diffusion and adversarial training.
Default
English
Tortoise TTS
1 voices
Premium
尝试模型
Multi-voice text-to-speech focused on quality with autoregressive architecture.
Random
English理解大赦国际的呼声
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.
多语言之声
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.
选择右声
最佳声音取决于您的使用案例。 对于音频书籍和播客, 使用自然流传的优异声音。 对于游戏字符, 探索不同模式的不同声音。 对于无障碍和屏幕阅读器, 选择清晰、 速度快的声音。 对于快速原型, 自由级的声音可以提供即时结果, 无需信用成本 。 在做出选择之前, 用播放按钮预览每个声音 。