| Name | Version | Summary | date |
| audiofeat |
1.0.0 |
A comprehensive PyTorch-based audio feature extraction library for machine learning, research, and audio analysis |
2025-08-04 04:54:45 |
| soe-vinorm |
0.1.6 |
An effective text normalization tool for Vietnamese |
2025-08-02 15:21:19 |
| deepctl |
0.1.10 |
Official Deepgram CLI for speech recognition and audio intelligence |
2025-08-01 15:23:11 |
| deepctl-cmd-transcribe |
0.1.10 |
Transcribe command for deepctl |
2025-08-01 15:23:07 |
| achatbot |
0.0.23 |
An open source chat bot for voice (and multimodal) assistants |
2025-07-29 06:44:53 |
| voice-mode |
2.17.2 |
VoiceMode - Voice interaction capabilities for AI assistants (formerly voice-mcp) |
2025-07-28 17:24:27 |
| auto-video-generator-mcp |
3.0.0 |
基于MCP协议的智能视频生成系统，支持自动添加字幕、语音合成和视频剪辑功能 |
2025-07-27 03:59:50 |
| senselab |
0.36.5 |
senselab is a Python package that simplifies building pipelines for speech and voice analysis. |
2025-07-25 18:39:55 |
| nemo-toolkit |
2.4.0 |
NeMo - a toolkit for Conversational AI |
2025-07-25 18:12:25 |
| whisper-parallel-cpu |
1.2.3 |
High-performance audio and video transcription using whisper.cpp with automatic model downloading and CPU parallelism |
2025-07-25 10:44:35 |
| mlx-voxtral |
0.0.2 |
Voxtral audio processing and model implementation for Apple Silicon using MLX |
2025-07-25 07:59:49 |
| modelscope |
1.28.1 |
ModelScope: bring the notion of Model-as-a-Service to life. |
2025-07-25 07:44:08 |
| phonexia-audio-quality-estimation-client |
1.0.0 |
Client for communicating with Phonexia audio quality estimation |
2025-07-21 08:39:56 |
| hume |
0.10.1 |
A Python SDK for Hume AI |
2025-07-17 22:03:09 |
| aiola |
0.1.2 |
The official Python SDK for aiOla API - Speech-to-Text and Text-to-Speech |
2025-07-17 14:53:09 |
| phonexia-grpc |
2.20.0 |
Library for communication with microservices developed by phonexia using grpc application interface. |
2025-07-17 09:33:17 |
| audiojudge |
0.1.2 |
A simple package for audio comparison using large language models |
2025-07-15 20:46:33 |
| parakeet-mlx |
0.3.5 |
An implementation of the Nvidia's Parakeet models for Apple Silicon using MLX. |
2025-07-13 17:19:58 |
| voice-mode-azure |
2.13.0 |
VoiceMode with Azure OpenAI support - Voice interaction capabilities for AI assistants |
2025-07-13 01:42:09 |
| vocals |
1.0.984 |
A Python SDK for voice processing and real-time audio communication |
2025-07-11 04:52:57 |