| Name | Version | Summary | date |
| achatbot |
0.0.25.post3 |
An open source chat bot for voice (and multimodal) assistants |
2025-09-18 15:51:51 |
| voice-mode |
4.5.0 |
VoiceMode - Voice interaction capabilities for AI assistants (formerly voice-mcp) |
2025-09-17 16:02:54 |
| parakeet-mlx |
0.3.7 |
An implementation of the Nvidia's Parakeet models for Apple Silicon using MLX. |
2025-09-17 13:37:44 |
| hume |
0.11.5 |
A Python SDK for Hume AI |
2025-09-16 16:30:44 |
| senselab |
0.43.0 |
senselab is a Python package that simplifies building pipelines for speech and voice analysis. |
2025-09-16 00:24:49 |
| megatron-bridge |
0.2.0rc3 |
Megatron Bridge: Training Recipes for Megatron-based LLM and VLM models |
2025-09-15 06:37:43 |
| faster-whisper-hotkey |
0.4.2 |
Push-to-talk transcription |
2025-09-14 11:47:50 |
| hybra |
2025.9.5 |
A module for trainable encoder/decoder filterbanks with auditory bias. |
2025-09-11 13:31:14 |
| soe-vinorm |
0.2.2 |
An effective text normalization tool for Vietnamese |
2025-09-07 00:37:33 |
| aiola |
0.2.0 |
The official Python SDK for aiOla API - Speech-to-Text and Text-to-Speech |
2025-09-04 11:48:18 |
| modelscope |
1.29.2 |
ModelScope: bring the notion of Model-as-a-Service to life. |
2025-09-02 09:53:27 |
| seed-vc |
0.4.3 |
Seed-VC: Zero-shot Voice & Style Conversion |
2025-09-02 07:12:16 |
| bournemouth-forced-aligner |
0.1.4 |
Bournemouth Forced Aligner - Phoneme-level timestamp extraction |
2025-09-02 02:48:33 |
| cascade-vad |
0.2.0 |
高性能异步并行VAD处理库 |
2025-08-31 06:20:03 |
| auditory-models |
0.1.1 |
Computation of auditory models |
2025-08-27 12:33:11 |
| ttsfm |
3.2.7 |
Text-to-Speech API Client with OpenAI compatibility |
2025-08-24 06:46:18 |
| phonexia-voiceprint-comparison-client |
1.5.0 |
Client for communication with Phonexia voiceprint comparison microservice. |
2025-08-21 14:25:07 |
| mlx-voxtral |
0.0.4 |
Voxtral audio processing and model implementation for Apple Silicon using MLX |
2025-08-19 13:41:00 |
| speechlight |
2.0.3 |
A lightweight Python library providing a common interface to multiple TTS and screen reader APIs. |
2025-08-17 23:58:29 |
| streamlit-voice-pipeline |
1.0.0 |
A Streamlit-ready voice pipeline for real-time conversation with OpenAI's GPT-4o Realtime API |
2025-08-16 08:01:27 |