模型目錄
比較可用模型,為創作任務選擇合適的模型。
Kitta AI 上的全部 AI 語音模型
Fish Audio
Use Fish Audio models on Kitta AI for multilingual speech and voice cloning through the workspace or API. The model family includes the open-source Fish Speech architecture; platform accounts, credits and API keys are managed independently.
MiniMax TTS
MiniMax Speech-02 is a state-of-the-art Chinese and multilingual TTS model from MiniMax AI. It delivers highly expressive, emotionally nuanced speech with industry-leading Chinese quality — available on Kitta AI alongside other top models.
Qwen TTS
Qwen TTS is Alibaba Cloud's large-scale text-to-speech model, part of the Qwen AI family. It delivers natural, expressive speech with strong Chinese and multilingual capabilities — now accessible on Kitta AI without any API setup.
IndexTTS
IndexTTS is an open-source industrial-grade text-to-speech model released by Bilibili. It achieves state-of-the-art voice cloning quality with a focus on consistency and naturalness across long-form content — available on Kitta AI.
CosyVoice
CosyVoice is an open-source multilingual TTS model from Alibaba DAMO Academy. It supports zero-shot voice cloning, cross-lingual synthesis, and fine-grained emotion control — making it one of the most versatile open-source TTS models available.
快速對比
為什麼用 Kitta AI 做 TTS?
一個平臺,覆蓋主流模型
一個賬號與 API Key 即可使用 Fish Audio、MiniMax、Qwen TTS、IndexTTS、CosyVoice。
免費上手
每月 2,000 免費 credits,無需信用卡即可體驗任意模型。
內置聲音克隆
不到一分鐘即可創建授權音色,並可在支持的模型中使用。
開發者 API
統一的 REST API 覆蓋所有模型,只需改一個參數即可切換模型。