kadirnar/VoiceHub

AI Summary: The task is to create a roadmap for the VoiceHub project, a unified inference interface for TTS models. This involves outlining future development goals and features for the project, potentially including support for new TTS models, improved performance, enhanced features, and addressing any outstanding issues.

AI Summary: Add support for the StyleTTS2 TTS model to the VoiceHub unified inference interface. This involves integrating the StyleTTS2 model, potentially requiring modifications to the `AutoInferenceModel` class to handle its specific input/output formats and parameters. Testing and documentation updates will also be necessary.

AI Summary: Add support for the ParlerTTS model to the VoiceHub unified inference interface. This involves integrating the ParlerTTS model's functionality into the existing `AutoInferenceModel` class, ensuring consistent usage with other supported models like OrpheusTTS, DiaTTS, and VuiTTS. The integration should include handling model loading, text processing, and audio generation, maintaining the existing simple and unified API.

AI Summary: Add support for the OuteTTS model to the VoiceHub unified inference interface. This involves integrating the OuteTTS model (available on GitHub and Hugging Face) into the existing `AutoInferenceModel` class, ensuring consistent usage with other supported models like OrpheusTTS, DiaTTS, and VuiTTS. This will likely require adapting the existing code to handle the specific input/output formats and parameters of OuteTTS.

AI Summary: Add support for the OpenVoice TTS model to the VoiceHub unified inference interface. This involves integrating the OpenVoice model into the existing `AutoInferenceModel` class, ensuring compatibility with the existing codebase and API, and adding necessary documentation and tests.

AI Summary: Add support for the OpenVoice TTS model to the VoiceHub unified inference interface. This involves integrating the OpenVoice model into the existing `AutoInferenceModel` class, ensuring compatibility with the existing API and adding necessary configuration options.

AI Summary: Add support for the MeloTTS TTS model to the VoiceHub unified inference interface. This involves integrating the MeloTTS model into the existing `AutoInferenceModel` class, ensuring consistent usage with other supported models, and updating documentation.

AI Summary: Add support for the Kokoro TTS model (https://github.com/hexgrad/kokoro, https://huggingface.co/hexgrad/Kokoro-82M) to the VoiceHub unified inference interface. This involves integrating the Kokoro model into the existing `AutoInferenceModel` class, ensuring consistent usage with other supported models, and updating documentation.

AI Summary: Integrate the GPT-SoVITS TTS model into the existing VoiceHub unified inference interface. This involves adding support for GPT-SoVITS's specific input/output formats and parameters within the `AutoInferenceModel` class, ensuring consistent usage with other models in VoiceHub.

AI Summary: Add support for the F5-TTS model to the VoiceHub unified inference interface. This involves integrating the F5-TTS model's inference capabilities into the existing `AutoInferenceModel` class, ensuring consistent usage with other supported models like OrpheusTTS, DiaTTS, and VuiTTS. This will likely require understanding the F5-TTS model's API and adapting the code to handle its specific input/output formats and parameters.

AI Summary: Add support for the CosyVoice TTS model to the VoiceHub unified inference interface. This involves integrating the CosyVoice model into the existing `AutoInferenceModel` class, ensuring consistent usage with other supported models, and updating documentation.

AI Summary: Add support for the ConversationTTS model to the VoiceHub unified inference interface. This involves integrating the ConversationTTS model into the existing `AutoInferenceModel` class, allowing users to utilize it with the same consistent API as other supported models (OrpheusTTS, DiaTTS, VuiTTS). This likely includes adding a new model type identifier and handling any specific requirements or differences in the ConversationTTS model's input/output format.

AI Summary: Add support for the Chatterbox TTS model to the VoiceHub unified inference interface. This involves integrating the Chatterbox model into the existing `AutoInferenceModel` class, allowing users to utilize it with the same consistent API as other supported models (OrpheusTTS, DiaTTS, VuiTTS). This likely requires understanding the Chatterbox model's API and adapting the VoiceHub code to handle its specific input/output formats and parameters.

AI Summary: Add support for the LLaSA TTS model to the VoiceHub unified inference interface. This involves integrating the model (available on Hugging Face and GitHub) into the existing `AutoInferenceModel` class, ensuring consistent usage with other supported models. The task requires understanding the LLaSA model's API and adapting the VoiceHub codebase to seamlessly incorporate it.