Appgithub-com-pierrunoyt-higgs-audio-v2-pinokio

Library Leaderboard

Log in Register

Higgs Audio V2 Enhanced

v1.0.0

https://github.com/PierrunoYT/Higgs-Audio-V2-Pinokioupdated 4/3/2026, 8:19:53 PMindexed 4/3/2026, 8:20:46 PM

Owner@pierrunoyt

Advanced text-to-speech with voice cloning, multi-speaker support, and background music generation using Higgs Audio V2

Typeapi

Community tagsLoading...

Sort

Loading…

Check-ins (1)

1 check-in

Platforms (1)

Windows100.0%

Arch (1)

x64100.0%

GPU (1)

nvidia geforce rtx 4090100.0%

RAM (1)

47GB100.0%

VRAM (1)

24GB100.0%

Recent commits

Add Higgs Audio V2 support with installation and usage documentation

PierrunoYT4 weeks ago88908fb

Refactor app.py to simplify Gradio UI initialization and enhance launch parameters. Removed theme and CSS from UI creation, allowing for dynamic assignment based on availability. Updated argument parsing to use environment variables for host and port configuration, improving flexibility in deployment.

PierrunoYT4 weeks ago2d05f18

Update app.py to load Gradio theme from a specified path, with fallback to default theme if the file is not found. Added logging for missing theme file to improve user awareness.

PierrunoYT4 weeks agocde8a45

Update app.py to support flexible imports for HiggsAudio components. Added a try-except block to handle different package layouts, ensuring compatibility with both higgs_audio and boson_multimodal. This change enhances the robustness of the application in varying environments.

PierrunoYT4 weeks ago5d40cec

Refactor app.py to enhance voice preset management and local model resolution. Introduced functions for resolving model and tokenizer paths, downloading voice preset files, and robustly extracting stop strings. Updated voice preset loading to prioritize local files and improved error handling. Removed deprecated voice example files and configuration.

PierrunoYT4 weeks ago5970dc3

Enhance app.py to support fallback for spaces module and improve demo launch parameters. The changes include a try-except block for importing the spaces module, providing a fallback implementation if it's unavailable. Additionally, the demo launch method has been updated to dynamically handle the inclusion of the mcp_server parameter based on its availability in the function signature. The install.js script has been cleaned up by removing the installation step for the spaces helper.

PierrunoYT4 weeks agof592c11

Add new Gradio UI for Text-to-Speech with HiggsAudioServeEngine

PierrunoYT4 weeks agoff40915

Update gradio_interface.py to enhance example prompts and parameter presets for voice cloning and dialogue generation. Introduced new examples for single-speaker and multispeaker voice descriptions, and refined existing prompts for clarity. Set default example to "smart-voice" for improved user experience.

PierrunoYT4 weeks agobb7c304

Refactor gradio_interface.py to streamline the Gradio UI initialization and enhance the stop_strings_from_table function. Improved handling of input types and error management, ensuring compatibility with both pandas DataFrames and list-like structures. Updated function calls for better clarity and modularity in the interface.

PierrunoYT4 weeks ago9376d3a

Refactor stop_strings_from_table function in gradio_interface.py to improve handling of pandas DataFrame and list-like inputs. Enhanced error handling and logging, ensuring robust fallback to default stop strings while maintaining clarity in the code structure.

PierrunoYT4 weeks ago9e445e3