CosyVoice 2 音声翻訳
Alibaba Tongyi Lab's streaming TTS reaching human-parity naturalness with near-zero latency and zero-shot cloning.
SSML タグでテキストを囲み、正確な制御を行う:
<speak><prosody rate="slow">Slow speech</prosody></speak>
選択したモデルが理解するタグ - クリックしてテキストにドラッグします:
このモデルは単純テキストを読み込み、インラインタグは無視されます。タグベースの感情を表現するには、Orpheus や Bark のような表現モデルに切り替えてください。
カスタム発音を定義 (単語=発音):
情報 CosyVoice 2
CosyVoice 2, from Alibaba's Tongyi Lab, was designed to make high-quality speech viable in real time. It uses a finite scalar quantization approach combined with flow matching to support streaming synthesis at extremely low latency, while reaching human-comparable naturalness that outperforms many commercial systems in subjective tests. Beyond quality, it offers zero-shot voice cloning from about 3 seconds of audio, cross-lingual synthesis, and fine-grained emotion control. Covering 8 languages with a 1,000-character cap, it's a strong fit for voice assistants, streaming TTS, and other real-time applications.
適合する: Real-time applications, streaming TTS, voice assistants
すべてブラウズ CosyVoice 2 声概要
- 開発者
- Alibaba (Tongyi Lab)
- ライセンス
- Apache 2.0
- 動物
- standard
- スピード
- medium
- 声のクローン
- はい
- 言語
- English, Chinese, Japanese, Korean, French, German, Italian, Spanish
- 最大文字数
- 1000