voiceprint

gmm-ubm voiceprint recognition by golang

On-device voice isolation, wake words, voice activity and voiceprints. In the browser (WebAssembly), Python, Android and iOS, with plugins for LiveKit Agents, Pipecat and Home Assistant (ESPHome, Wyoming). No server, no key. Apache-2.0 code and weights.

Speaker recognition ,Voiceprint recognition

Voice biometric authentication PAM module for Linux

一款完全开源的场景自适应的 AI 语音输入工具，自动识别应用切换场景，支持语音唤醒、自定义规则、声纹识别。

涛声 TaoSheng：用一部安卓手机全天收音 → 转写 → 认人 → AI 整理成待办与记忆。无需硬件、无需账号，数据只在你手机里。

Enhanced `audio-transcribe` skill with cross-session voiceprint matching (enroll → match → merge) for multi-speaker meeting & podcast transcription. FunASR + CAM++ diarization + optional LLM cleanup, works with Claude Code.

speaker recognition / speaker verification models in pytorch implementation

ESP32-P4 AI 会议秘书：语音闲聊 + 会议实时转写/纪要 + 声纹区分发言人（固件 + 自托管后端）

声纹注册、验证与评测工具包：声学基线、注册库、开放集识别、EER/minDCF 和可复现实验。

Self-hosted GPU transcription service with persistent speaker voiceprints

Steal any brand's voice from their website. Deployable VOICE.md in seconds. Zero deps, zero API keys.

Clone a voice in 5 seconds to generate arbitrary speech in real-time

Offline-first audio/video transcription and speech synthesis for Linux & Windows, with voiceprints, voice cloning, illustrated exports, optional Ollama transcript rewriting, and local Web UI/APIs.

Utterance-level Aggregation For Speaker Recognition In The Wild

本地运行的直播/视频字幕生成与校对工具：多引擎识别、单目标声纹、BGM 判别、歌曲歌词对齐，配 Electron 双轨时间轴编辑器

Swedish Spontaneous Speech Data

Finnish Spontaneous Speech Data

Speaker recognition and speech-to-text platform with voiceprint identification, multi-speaker transcription, and meeting audio understanding.

Burmese Spontaneous Speech Data