Instructions to use IndexTeam/Index-TTS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- IndexTTS
How to use IndexTeam/Index-TTS with IndexTTS:
# Download model from huggingface_hub import snapshot_download snapshot_download(IndexTeam/Index-TTS, local_dir="checkpoints") from indextts.infer import IndexTTS # Ensure config.yaml is present in the checkpoints directory tts = IndexTTS(model_dir="checkpoints", cfg_path="checkpoints/config.yaml") voice = "path/to/your/reference_voice.wav" # Path to the voice reference audio file text = "Hello, how are you?" output_path = "output_index.wav" tts.infer(voice, text, output_path)
- Notebooks
- Google Colab
- Kaggle
Add pipeline tag
#1
by nielsr HF Staff - opened
This PR makes the model discoverable at https://huggingface.co/models?pipeline_tag=text-to-speech&sort=trending.
there are some usage notes:
- The first version currently supports Chinese and English, under the Apache-2.0 license.
- Please pre-process the input text, like converting numbers. Currently, it only accepts simplified Chinese characters, English words and several common punctuations.
index-tts changed pull request status to merged