multi-speaker 开源项目推荐（38 个）

mikebrady /shairport-sync

AirPlay 和 AirPlay 2 音频播放器

netease-youdao /EmotiVoice

EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine

r9y9 /deepvoice3_pytorch

PyTorch implementation of convolutional neural networks-based text-to-speech synthesis models

fluxions-ai /vui

实时语音助理-WebREC流媒体、更快耳语的ASB、本地LLM、Vui Nano（300 M）TTC。OpenAI实时API兼容。语音克隆，强行插入，4090上~9倍实时。阿帕奇2.0。

ranchlai /mandarin-tts

中文普通话 中文 语音合成，由fastspeech 2 开发，使用 pytorch 实现，使用 waveglow 作为语音编码器，使用biaobei和aishell3数据集

DrewThomasson /VoxNovel

VoxNovel: generate audiobooks giving each character a different voice actor.

keonlee9420 /Comprehensive-Transformer-TTS

A Non-Autoregressive Transformer based Text-to-Speech, supporting a family of SOTA transformers with supervised and unsupervised duration modelings. This project grows with the research community, aiming to achieve the ultimate TTS

aishoot /LSTM_PIT_Speech_Separation

Two-talker Speech Separation with LSTM/BLSTM by Permutation Invariant Training method.

keonlee9420 /Comprehensive-E2E-TTS

A Non-Autoregressive End-to-End Text-to-Speech (text-to-wav), supporting a family of SOTA unsupervised duration modelings. This project grows with the research community, aiming to achieve the ultimate E2E-TTS

JaySpiffy /draft-to-take

Draft to Take 测试版：本地优先的AI音频制作工作室，支持IndexTTS2、Docker、Qwen、OmniVoice、SFX、氛围音和音乐副车支持。

anton-jeran /MULTI-AUDIODEC

This is the official implementation of our multi-channel multi-speaker multi-spatial neural audio codec architecture.

Totoketchup /Adaptive-MultiSpeaker-Separation

Adaptive and Focusing Neural Layers for Multi-Speaker Separation Problem

keonlee9420 /Comprehensive-Tacotron2

PyTorch Implementation of Google's Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions. This implementation supports both single-, multi-speaker TTS and several techniques to enforce the robustness and efficiency of the model.

FirmwareVersion /choravox

Offline multi-speaker meeting-speech toolkit: planted-ground-truth synthetic meeting factory, VAD, speaker embeddings, diarization (AHC/spectral/VB-HMM), overlap detection, CTC speaker-attributed ASR, cpWER/DER/JER evaluation, online streaming mode, deterministic reports. NumPy core, CPU-only torch extra.

TheSeraphim /scribe-forge-ai

🎵 Complete offline audio transcription system with speaker diarization using OpenAI Whisper and PyAnnote. Features automatic audio cleaning, precise timestamps, multiple output formats (JSON/TXT/Markdown), and support for 20+ audio formats. No external APIs required - works entirely offline.

hwRG /FastSpeech2-Pytorch-Korean-Multi-Speaker

Multi-Speaker FastSpeech2 applicable to Korean. Description about train and synthesize in detail.

TaurenMountain /DAVE

DAVE: audio-visual speech enhancement & target speaker extraction for real-world meetings — audio-only TIGER-M backbone (2.56M) + four-cue speaker attribution. ISCSLP 2026 AVSE Challenge: Track1 4th, Track2 3rd.

nikitashvarts /CocktailPartySpeakerRecognition

An Algorithm for Speaker Recognition in a Multi-Speaker Environment

ZoraizQ /urdu-speech-recognition

Urdu Speech Recognition using Kaldi ASR, by training Triphone Acoustic GMMs using the PRUS dataset.

NickYCLin /story-voice

自架式 EPUB／TXT 多角色有聲書製作工具，提供角色分析、人工審核、聲線編排與 TTS 產製。