[KongchangAI]
ModelIndexTTS2.0

IndexTTS 2.0

The second-generation text-to-speech model open-sourced by Bilibili, supporting zero-shot voice cloning and fine-grained emotion control; users can provide a short reference audio clip to imitate a timbre and read arbitrary text aloud.

Timeline (last 90 days)

Oct 30

IndexTTS 2.0 is a text-to-speech (TTS) model open-sourced on Bilibili, the second-generation version of the IndexTTS series, emphasizing zero-shot voice cloning and fine-grained emotion control.

Unverified50%
Oct 30

Bilibili UP host "登录仓" created a long-form script workbench for the IndexTTS 2.0 super-optimized integrated package, and the project is open source.

Unverified50%
Oct 30

The workbench provides a multitrack editing interface that references CapCut's editing features and uses IndexTTS 2.0's emotion control capability to adjust emotion and regenerate.

Unverified50%
Oct 30

The workbench installation process is: download the zip package from the GitHub Release page, place it into the IndexTTS 2.0 integrated package directory and extract it to overwrite, run the install script, then double-click the Start launch script to run the project.

Unverified50%
Oct 30

The IndexTTS 2.0 "super-optimized integrated package" refers to a ready-to-use zip package in which the community or a UP host has packaged the model, dependency environment, and inference scripts, so users can run it locally after extracting.

Unverified50%

All Facts (5)

Source Articles