> For the complete documentation index, see [llms.txt](https://gzbin.gitbook.io/map/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://gzbin.gitbook.io/map/algorithm/voice.md). # Audio 语音 音频 Voice speech Sound autotune [**基于CNN的歌声合成算法论文解读**](https://cloud.tencent.com/developer/article/1776840) [**NEUTRINO**](https://n3utrino.work) [**linux下python文字转语音库pyttsx3用法**](https://www.bilibili.com/video/av67394684/) Python实现语音合成 [zminoooooo](https://www.bilibili.com/video/BV1gu411R7L1) 使用百度api 35:00 开始 Python文字语音播报 [**书童**](https://xugaoxiang.com/2021/04/08/python-tts-chinese/) LumenVox - Exceptional Voice Experiences [u](https://www.youtube.com/channel/UCe3Gq1lw94FjwDmy6aGVn_A/videos) | | | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Deep Learning for Human Language Processing (2020,Spring) [Hung-yi Lee](https://www.youtube.com/playlist?list=PLJV_el3uVTsO07RpBYFsXg-bN5Lu0nhdG) | | | | Understanding Sound & Speakers [Branch Education](https://www.youtube.com/playlist?list=PL6rx9p3tbsMvYWeYUTNuRNMLXn0eyJvub) | | Simple Voice Recorder with GUI in Python [NeuralNine](https://www.youtube.com/watch?v=u_xNvC9PpHA) | | 深度学习-语音识别实战(Python) [网易云课堂](https://study.163.com/course/courseMain.htm?courseId=1210361865) | | Valerio Velardo - The Sound of AI([u](https://www.youtube.com/c/ValerioVelardoTheSoundofAI/featured), [medium](https://medium.com/the-sound-of-ai), [linkedin](https://www.linkedin.com/in/valeriovelardo), [fb](https://www.facebook.com/TheSoundOfAI), [s](https://valeriovelardo.com), ) | | Deep Learning (for Audio) with Python([ulist](https://www.youtube.com/playlist?list=PL-wATfeyAMNrtbkCNsLcpoAyBBRJZVlnf), ) | | speech recognition [pixeldev](https://www.youtube.com/playlist?list=PLsaLbFPkNd55uUF-MpQ7RtldorYYR_CeT) | | [讯飞听见](https://www.iflyrec.com/) | | Audacity [s](https://www.audacityteam.org/) [v](https://www.youtube.com/watch?v=P30suV1UdSY) [doc](https://manual.audacityteam.org) shop 音频处理软件 [v](https://www.youtube.com/playlist?list=PLlKpQrBME6xKm9iJlVHWbJd_xAvtAQy6W) [v](https://www.youtube.com/playlist?list=PLMoVDOzX4VcQGOySLj7TO3ab0g1eIzJYq) | | aeneas s [git](https://github.com/readbeyond/aeneas) [doc](https://www.readbeyond.it/aeneas/) 用于自动同步音频和文本（也称为强制对齐）的工具 | | 音频处理\|adobe audition cc 2020\|零基础教程 [长安老张](https://www.youtube.com/playlist?list=PLnIffqrKafFuF7r4aej24Zg2X0drpEc5e) | | 音频编辑处理\|Adobe Audition CC 2019\|零基础教程 [长安老张](https://www.youtube.com/playlist?list=PLnIffqrKafFszIyQmLnHDhfpVExbtoYGp) | | 文字转语音--让机器语音像人类一样自然真实 [长安老张](https://www.youtube.com/watch?v=SdhLawZEr1I) | | Desmos Shenanigans [Eric Tao](https://www.youtube.com/playlist?list=PLlYltssWVRe9vOW7BmghfExRg2jPMqiQH) | | Simple Voice Recorder in Python [NeuralNine](https://www.youtube.com/watch?v=av8E8qLZswU) pyaudio wave | | Guitars AI [u](https://www.youtube.com/c/GuitarsAI/playlists) [git](https://github.com/GuitarsAI/) | | Multirate Signal Processing with Python [Guitars AI](https://www.youtube.com/playlist?list=PL6QnpHKwdPYiQmq8PcGvx-EpLFrVmYMOW) [git](https://github.com/GuitarsAI/MRSP_Notebooks) | | Python for Beginner: Basics of Digital Audio Processing and Machine Learning using Python [Guitars AI](https://www.youtube.com/playlist?list=PL6QnpHKwdPYi-600wCa4PPIrP2DpgKqFk) | |

Machine Learning for Audio Signals in Python - Full Course - Ilmenau University of Technology Guitars AI

Machine Learning for Audio Signals in Python Guitars AI git

| | Advanced Digital Signal Processing using Python [Guitars AI](https://www.youtube.com/playlist?list=PL6QnpHKwdPYhIt-zvYMSYXzLpQ0MMRVTK) [git](https://github.com/GuitarsAI/ADSP_Tutorials) | | speechbrain/[speechbrain](https://github.com/speechbrain/speechbrain) A PyTorch-based Speech Toolkit [s](https://speechbrain.github.io/) [s](https://www.zhihu.com/question/266242493) | | 从语音识别到语音交互 陈伟 [青云QingCloud](https://www.youtube.com/watch?v=AUKycdq6jig) | | Talk \| 字节跳动研究员董倩倩：基于单调切分的端到端同传 [将门-TechBeat技术社区](https://www.youtube.com/watch?v=uv_4sRg47hk) | | Talk \| 中国科学技术大学和微软亚洲研究院联合培养博士生冷燚冲：语音识别的快速纠错模型FastCorrect [将门-TechBeat技术社区](https://www.youtube.com/watch?v=uYaeOM6_4Go) | | How to do entity detection on audio files with Python [AssemblyAI](https://www.youtube.com/watch?v=7jrs3DrMVJQ) | | Audio Signal Processing for Machine Learning and Deep Learning [Prabhjot Gosal](https://www.youtube.com/playlist?list=PLvELbYeZ7GEHBaoCyZS63FhI0bbhnwZbB) | | oscilloscope [search](https://www.douyin.com/search/oscilloscope) | | Audio Spectrum Analyzer [Mark Jay](https://www.youtube.com/playlist?list=PLX-LrBk6h3wQVsrldsQdtKmeTygurKiuS) | | Python - Read WAV file SMN [DigiTech](https://www.youtube.com/watch?v=ZBS31QxVvSg) | | Audio processing in Python with Feature Extraction for machine learning [Prodramp](https://www.youtube.com/watch?v=vbhlEMcb7RQ) | | Extract Features from Audio File \| MFCC \| Python [Hackers Realm](https://www.youtube.com/watch?v=hX2sOvrWC1Q\&list=PL_8jNcohs27XTz6sGUZaQjXULA1J-Vun7\&index=124) | | Basic Sound Processing in Python \| SciPy 2015 \| Allen Downey [Enthought](https://www.youtube.com/watch?v=0ALKGR0I5MA) | | Extract Musical Notes from Audio in Python with FFT [Jeff Heaton](https://www.youtube.com/watch?v=rj9NOiFLxWA) | | Music Production with FL Studio – Full Tutorial for Beginners [freeCodeCamp](https://www.youtube.com/watch?v=BUjdnxgBgzM) | | Sorting Visualizer with Sound (JavaScript Tutorial) [Radu Mariescu-Istodor](https://www.youtube.com/watch?v=_AwSlHlpFuc\&t=27s) | | #219 Generating sounds 🎵 from the PICO! But is it music to my 👂 ears? [Ralph S Bacon](https://www.youtube.com/watch?v=9H6zeZcrZ7M) | | AI sound bites series for media pickup [Dr Alan D. Thompson](https://www.youtube.com/playlist?list=PLqJbCeNOfEK-81jVeTcG9MHLfgeFkLlVm) | | 文字转语音、音频转文字软件！双向转换，完全免费开源！支持 Windows、macOS、Linux \| [零度解说](https://www.youtube.com/watch?v=MP_tjvFq3m0) | | 注意看，这些全是 AI 配音。 [Topbook](https://www.youtube.com/watch?v=yUuS-oTDSD4) | | 中国传媒大学\_\_播音主持普通话语音 [知识资源世界(KnowledgeWorld)](https://www.youtube.com/playlist?list=PLoEWjLHPG6Z4J3SZWxrDH-xpythKiXyim) | |

Audio Slicer 音频切片机 一个简约的 GUI 应用程序，通过静音检测对音频进行切片。

flutydeer/audio-slicer v

| | Transcribe Audio Files with OpenAI Whisper [NeuralNine](https://www.youtube.com/watch?v=UAdX0cGuC28) | | Convert Videos To MP3 in Python [NeuralNine](https://www.youtube.com/watch?v=ucXTQ0V8qMA) | | | | | | | *** ## Audio Classify | | | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | Build a Deep Audio Classifier with Python and Tensorflow [Nicholas Renotte](https://www.youtube.com/watch?v=ZLIPkmmDJAc) | | MIT 6.S191: Automatic Speech Recognition [Alexander Amini](https://www.youtube.com/watch?v=sR6_bZ6VkAg) | |

Complete Deep Learning

Krish Naik

Part 1-EDA-Audio Classification Project Using Deep Learning

Part 2-Data Preprocessing-Audio Classification Project Using Deep Learning

Part 3-Model Creation-Audio Classification Project Using Deep Learning

Part 4-Testing ANN Model-Audio Classification Project Using Deep Learning

| | | | | | | ## 语音识别, ASR, Automatic Speech Recognition **Speech to Text /** Speech Recognition **/** Voice Recognition / Speech Detection 语音转文字 | | | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | vosk | | paddle speech | | SpeechRecognition [pypi](https://pypi.org/project/SpeechRecognition/) [git](https://github.com/Uberi/speech_recognition) [v](https://www.youtube.com/watch?v=31DZfkYRvI4) | | PyAudio [**s**](http://people.csail.mit.edu/hubert/pyaudio/#downloads) | | Speech Recognition with Convolutional Neural Networks in Keras/TensorFlow [Weights & Biases](https://www.youtube.com/watch?v=Qf4YJcHXtcY) | | Automatic Speech Recognition - An Overview [Microsoft Research](https://www.youtube.com/watch?v=q67z7PTGRi8) [s](https://www.microsoft.com/en-us/research/video/automatic-speech-recognition-overview/) | | I Built a Personal Speech Recognition System for my AI Assistant [The A.I. Hacker - Michael Phi](https://www.youtube.com/watch?v=YereI6Gn3bM) | | A Basic Introduction to Speech Recognition (Hidden Markov Model & Neural Networks) [Hannes van Lier](https://www.youtube.com/watch?v=U0XtE4_QLXI) | | Voice Recognition As Fast As Possible [Techquickie](https://www.youtube.com/watch?v=AWWjN1QqoYY) | | Phoneme Detection with CNN-RNN-CTC Loss Function - Machine Learning [Ali Yektaie](https://www.youtube.com/watch?v=x1IAPgvKUmM) | | how speech recognition works in under 4 minutes. [Sam Stork](https://www.youtube.com/watch?v=iNbOOgXjnzE) | | Automatic Speech Recognition: Chapter 1 [NEWTON Technologies](https://www.youtube.com/watch?v=vlr_3kNQZAk) | |

Lecture 9 - Speech Recognition (ASR) \[Andrew Senior] Zafarullah Mahmood

Deep Learning for NLP at Oxford with Deep Mind 2017 Zafarullah Mahmood

| | Python Speech Recognition Project Series [AssemblyAI](https://www.youtube.com/playlist?list=PLcWfeUsAys2nb0i79L_LqYVfwOWEYA4eD) | |

Speech Recognition in Python Tutorial – Full Course for Beginners freeCodeCamp

Python Speech Recognition Tutorial – Full Course for Beginners

| | Speech Recognition in Python [NeuralNine](https://www.youtube.com/watch?v=9GJ6XeB-vMg) | | Build your own real-time voice command recognition model with TensorFlow [AssemblyAI](https://www.youtube.com/watch?v=m-JzldXm9bQ) | | nobody132/[masr](https://github.com/nobody132/masr) 中文语音识别; Mandarin Automatic Speech Recognition; | | Build a Twitter Hate Speech Detection Model Using Machine Learning \| Python \| Project For Beginners [AI Sciences](https://www.youtube.com/watch?v=AEWty_y_WxE) | | Hate Speech Detection on Twitter Using Sentiment Analysis and Machine Learning Algorithms. [Vikas Mayurkumar Patel](https://www.youtube.com/watch?v=oJ_nX5jsfIY) colab | | JSALT 2020 Workshop Closing Ceremonies: Speech Recognition and Diarization for Unsegmented Multi-talker Recordings Team Presentation [Center for Language and Speech (CLSP) @ JHU](https://www.youtube.com/playlist?list=PLSeS0sl8xpTz705M-KK7s6VT19a99SsFT) | |

Conformer-1: a new large scale/robust speech recognition model AssemblyAI

Conformer-2: A state-of-the-art speech recognition model AssemblyAI

| | 【Whisper】免費開源語音辨識自動上字幕　字幕正確率比剪映還高！！！｜下載完後無須聯網　僅需使用自己電腦處理｜如何在Windows上使用Whisper [The walking fish 步行魚](https://www.youtube.com/watch?v=kFtrvdriLU8) | | 【Code Gym】Python 文字轉語音教學，用短短幾行程式，做出會讀文字說話的自動化服務 [Code Gym](https://www.youtube.com/watch?v=0PuslZHJQes) | | 教你写一款简单的语音识别软件 [程序马](https://www.youtube.com/watch?v=4A3NAYgz-R8) | | 语音识别小程序 识别中英文语音转文字 附python code源码 [人工智障机器人](https://www.youtube.com/watch?v=dPiZG0yM5H4) | | 【免費！極速！上字幕！】5分鐘完成8小時的工作量！ [木石mushi](https://www.youtube.com/watch?v=8tjbHfkO9bU\&list=PLi3JGBubTe7YtBHGuc5Gj9NfwIsWqnG4o) 剪映 | | 阿里达摩院paraformer 中文语音识别 [v](https://www.youtube.com/watch?v=8gd_WtBPxaw) | | Speech recognition in Python made easy \| Python Tutorial [AssemblyAI](https://www.youtube.com/watch?v=YdYTSxEW5bA) | | | | | | pyTranscriber | | | | ------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------- | - | | raryelcostasouza/[pyTranscriber](https://github.com/raryelcostasouza/pyTranscriber) generate automatic transcription / automatic subtitles | [069ba4a500](https://github.com/raryelcostasouza/pyTranscriber/tree/069ba4a500f9e37df2bfb31ea1a4627fbc82ca78) | | | | | | | | | | ### **NVIDIA JARVIS** | | | ----------------------------------------------------------------------------------------------------------------------------------------- | | **NVIDIA JARVIS(**[**s**](https://developer.nvidia.com/nvidia-jarvis?ncid=partn-38053#cid=dl20_partn_en-us)**, )** | | **NVIDIA Jarvis Conversational AI on Python - Dr. Ahmad Bazzi(**[**v**](https://www.youtube.com/watch?v=sbYolIax190)**, )** | | **Conversational AI w/ Jarvis - checking out the API(**[**sentdex**](https://www.youtube.com/watch?v=fQzjgaKSrkc)**, )** | | **1. Live coding Jarvis Transcriptions for Speech to Text Dataset p.1(**[**sentdex**](https://www.youtube.com/watch?v=ubvgReZVf5g)**, )** | | **2. Live coding Jarvis Transcriptions for Speech to Text Dataset p.2(**[**sentdex**](https://www.youtube.com/watch?v=BDl6fzhp2Ao)**, )** | | | | ------------------------------------------------------------------------------------------------------------------------------------------------------- | | How to Convert Speech To Text In Python \| Speech Recognition Library \| 10 Lines Of Code [Know-How](https://www.youtube.com/watch?v=ifey3EnhB-g) | | How To Convert Text To Speech In Python \| pyttsx3 Library \| Basics Of Artificial Intelligence [Know-How](https://www.youtube.com/watch?v=6Za0ztPMr8g) | ## 语音合成 SpeechSynthesis, Audio Generation Voice Synthesis | | | --------------------------------------------------------------------------------------------------------------------------- | | AI Voice Synthesis [NanoNomad](https://www.youtube.com/playlist?list=PLn3gJVMORUsTiGp5Jc37XID9jS9SHKUV1) | | ai实时变音，你的声卡能否一战！#人工智能 #aigc #有ai就有无限可能 #ai [AICK-KC](https://www.douyin.com/video/7249742859941776651) | | How To Create AI Voice Over [How To In 5 Minutes](https://www.youtube.com/playlist?list=PLIi08al-Zd_kixb8cTdoOWsQvTTrNh0aR) | | | ## **TTS Text to Speech** | | | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | pdf to voice [v](https://www.douyin.com/video/7150605317326245151) | | 魔音工坊 [s](https://www.moyin.com/) | | 逗哥 云浩宇 解说模式 | | VoiceMaker [s](https://voicemaker.in/) [v](https://www.youtube.com/watch?v=X-DacDX3W8M) | | NaturalReaders [s](https://www.naturalreaders.com/online/) 无中文 英文发音好 | | narakeet [s](https://www.narakeet.com/app/text-to-audio) [s](https://www.narakeet.com/languages/chinese-text-to-speech/) Zihan Daoming | | play.ht [s](https://play.ht/text-to-speech-voices/chinese/) 下载付费 带情绪 Zhiyu Yunxi Xiaoyou Xiaoxuan Xiaoxiao | | IBM Watson Text to Speech [s](https://www.ibm.com/cloud/watson-text-to-speech) | | chineseedge [s](https://chineseedge.com/chinese-text-to-speech/) 单一 高亮 | | imtranslator [s](https://text-to-speech.imtranslator.net/) 一般 | | Kukarella [v](https://www.youtube.com/watch?v=a6bVPAz2L3s) [s](https://kukarella.com/) | | 百度 api paddlepaddle/[PaddleSpeech](https://gitee.com/paddlepaddle/PaddleSpeech) | | Balabolka [s](http://balabolka.site/cn/balabolka.htm) [v](https://www.youtube.com/watch?v=kfqpFKdDVMU) TTS程序 api调用 不支持linux | | ranchlai/[mandarin-tts](https://github.com/ranchlai/mandarin-tts) 中文 (普通话) 语音 合成 | | espeak [s](http://espeak.sourceforge.net/index.html) | | ubuntu完美安装espeak支持中文和粤语 [csdn](https://blog.csdn.net/qq_24406903/article/details/89811732) caixxiong/[espeak-data](https://github.com/caixxiong/espeak-data) | | clipchamp [s](https://clipchamp.com/en/) [v](https://www.youtube.com/watch?v=TQDbtP5SB00) 语音需要从视频中提取 | | 【全球10大机器配音软件】有声书影视解说博主利器\|全球10大语音合成软件 软件侠何二 | | 一款采用人工智能黑科技文字转流畅自然配音软件配音神器 [廉飞](https://www.youtube.com/watch?v=jd1WOkBIOTQ) | | 听书、看书、搜书（小说），一个视频教你全搞定！从此你就是大神！几千万书源，AI智能朗读 [嘴哥干货](https://www.youtube.com/watch?v=jI3yo0fXusw) | | Harmonai, Dance Diffusion and The Audio Generation Revolution [Weights & Biases](https://www.youtube.com/watch?v=KmB8z2CYjZY) | | [**语音合成-腾讯云**](https://cloud.tencent.com/developer/tag/10464) | | How to make text to speech from your own voice with python [TheLazyBusyGamer](https://www.youtube.com/watch?v=h-M1kqL4C7c) | | 我花了15小時，就為找到這3款AI語音生成工具｜AI朗读｜AI虚拟主播 [指令必达](https://www.youtube.com/watch?v=RsnU0Pjt7lo) | | 【Anny讲Python】Python听书系统之语音合成技术 [Python学习指南](https://www.youtube.com/watch?v=A4qZzbFldyk) pytts 百度api | | | |

suno-ai/bark

文字轉語音，堪比人聲！100%相似，完全找不到AI的痕跡！Bing Chat將擁有長期記憶😱 ChatGPT更新！ 你的攝影大哥 Davidddodle bark

| | 2 Build Your Own Audiobooks App ! python projects 2023 ! Master Python by Building Real World Python [Self Study](https://www.youtube.com/watch?v=WBRL0gcZ1cg) pyttsx3 | | 最强TTS（文本转语音）模型Bark发布 - 支持带有情感的语音，歌曲生成 -体验声音克隆功能 [小薇 Official Channel](https://www.youtube.com/watch?v=lz9YPR1vq60) huggingface space | | 文本转语音的逼真程度再次突破天花板！Bark横空出世 The realism of text-to-speech conversion technology reached new heights! [工具狂Toolbuddy](https://www.youtube.com/watch?v=nUKXo_iLnZY) | | AI工具 免费可商用的AI克隆声音 语音合成 文字转语音 手把手教学 bark #bark #AI语音 #声音克隆 #AI克隆 #创业工具 [AB视界](https://www.youtube.com/watch?v=LJaWU5yPJao) | | | | | | | | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Ekho [s](https://www.eguidedog.net/ekho.php) [git](https://github.com/hgneng/ekho) 支持linux [为Ekho添加新的声音](http://eguidedog.net/doc/doc_make_new_voice_cn.php) [linuxInstall](https://www.eguidedog.net/doc/doc_install_ekho.php) [2](https://blog.csdn.net/cceking/article/details/51760732) [编译安装](https://blog.csdn.net/AMDS123/article/details/73825409) | | TTS技术简单介绍和Ekho（余音）TTS的安装与编程 [csdn](https://blog.csdn.net/zouxy09/article/details/7909154) | | Cloud Text-to-Speech Google Cloud | | gTTS (Google Text-to-Speech) [doc](https://gtts.readthedocs.io/en/latest/) [git](https://github.com/pndurette/gTTS) | | 自定义声音模型 📱文字转语音--先从克隆自己的声音开始\|20分钟合成自己的声音 [长安老张](https://www.youtube.com/watch?v=X3opZ6-tb-o) | | How to Generate Your Own Voice - Text to Speech [Website Learners](https://www.youtube.com/watch?v=PzBdEW5WNGo) | | Can we CLONE my voice using ML? [Nicholas Renotte](https://www.youtube.com/watch?v=qVD1NBLoOJw) | | I secretly used AI to clone my favourite Rapper [Nicholas Renotte](https://www.youtube.com/watch?v=HoMZxHNpM84) | | [**Real-Time-Voice-Cloning**](https://github.com/CorentinJ/Real-Time-Voice-Cloning) | | NVIDIA’s Amazing AI Clones Your Voice! 🤐 [Two Minute Papers](https://www.youtube.com/watch?v=k54cpsAbMn4) | | Microsoft’s New AI Clones Your Voice In 3 Seconds! [Two Minute Papers](https://www.youtube.com/watch?v=F6HSsVIkqIU) | | My Vocal.AI s [v](https://www.youtube.com/watch?v=lz9YPR1vq60) | | AI工具 五秒声音克隆 mockingbird 支持中文 [AB视界](https://www.youtube.com/watch?v=eHRHfYeoZ3g) | | 只需5秒！就能克隆你的声音，MockingBird 轻松实现 AI 文字转语音 ！附最新安装、使用教程！\| [零度解说](https://www.youtube.com/watch?v=dxIvkEB0XE0) | | 我把自己做成了AI声库，效果太离谱了!! 给朋友打“诈骗电话”会被发现吗？ ｜ [LKs](https://www.youtube.com/watch?v=ezt3dQac3w4) | | AI声音克隆 [AI工坊#十个骑士](https://www.youtube.com/playlist?list=PL4HQtsL6idnZbBWq18aO5uXxgRd7M8zUh) | | | | | | | | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Azure 文档 [microsoft](https://docs.microsoft.com/zh-cn/azure/?product=popular) | | azure 语音服务文档 [microsoft](https://docs.microsoft.com/zh-cn/azure/cognitive-services/speech-service/) 语音服务[定价](https://azure.microsoft.com/zh-cn/pricing/details/cognitive-services/speech-services/) [试用](https://azure.microsoft.com/zh-cn/services/cognitive-services/text-to-speech/#features) 试用[精简版](https://speech.microsoft.com/audiocontentcreation) | | azure 文本转语音 [microsoft](https://azure.microsoft.com/zh-cn/services/cognitive-services/text-to-speech/#overview) | | Azure-Samples/[cognitive-services-speech-sdk](https://github.com/Azure-Samples/cognitive-services-speech-sdk) [Python](https://github.com/Azure-Samples/cognitive-services-speech-sdk/tree/master/quickstart/python/text-to-speech) | | Build a natural custom voice for your brand [microsoft](https://techcommunity.microsoft.com/t5/ai-cognitive-services-blog/build-a-natural-custom-voice-for-your-brand/ba-p/2112777) Neural TTS [u](https://www.youtube.com/channel/UCxZ5iCrcXbpmdhZIKFKgMLA/videos) | | Microsoft Azure Open Course (Mandarin) By MVP张诚 [Cheng Zhang](https://www.youtube.com/playlist?list=PLZmpc0o_yCMkHVSVdNSi4lfgzf40UyeiR) | | articles with label Neural TTS [microsoft](https://techcommunity.microsoft.com/t5/ai-cognitive-services-blog/bg-p/CognitiveServicesBlog/label-name/Neural%20TTS) | | articles with label Speech [microsoft](https://techcommunity.microsoft.com/t5/ai-cognitive-services-blog/bg-p/CognitiveServicesBlog/label-name/Speech) | | Artificial Intelligence and Machine Learning [microsoft](https://techcommunity.microsoft.com/t5/artificial-intelligence-and/ct-p/AI) | | articles with label Cognitive Services [microsoft](https://techcommunity.microsoft.com/t5/ai-cognitive-services-blog/bg-p/CognitiveServicesBlog/label-name/Cognitive%20Services) | | Neural Text to Speech extends support to 15 more languages with state-of-the-art AI quality By Qinying Liao [microsoft](https://techcommunity.microsoft.com/t5/ai-cognitive-services-blog/neural-text-to-speech-extends-support-to-15-more-languages-with/ba-p/1505911) | | Neural Speech Synthesis with Transformer Network [arxiv](https://arxiv.org/abs/1809.08895) | | FastSpeech: Fast, Robust and Controllable Text to Speech [arxiv](https://arxiv.org/abs/1905.09263) | | 微软AI配音，免费的文字转音频在线工具 [便利空间](https://www.youtube.com/watch?v=I7TRD9mjW1c) | | | | | ## voice 2 voice ### AI音色替换技术(Sovits4.0) | | | | | | ------------------------------------------------------------------------------------------------------------------------------------------------------------- | --- | --- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | voice 2 voice | | | | | AI孙燕姿 [u](https://www.youtube.com/@AI-nx9lp/videos) 华语AI翻唱 [u](https://www.youtube.com/@AImusicCover4u) | | | | | 【AI翻唱】“超详细”！Sovits4.0手把手详细教学！ [StarPorridge小粥](https://www.youtube.com/watch?v=VTWTQ5l9eHI) | | | | | 从孙燕姿的“漠河舞厅”谈生成式AI创作 [Jeff科技视角](https://www.youtube.com/watch?v=x3DwYWqlY5k) Jarret Charvis | | | | | AI孙燕姿，再次席卷乐坛。版权律师们，愁白了头。 [老范讲故事](https://www.youtube.com/watch?v=322Al2O6Dz8) | | | | | 面向小白的低成本的VITS模型训练教程及注意事项 [欧皇张大千](https://www.youtube.com/watch?v=hnxPPDw5fWE) colab | | | | | Voice Cloning Tutorial with Coqui TTS and Google Colab \| Fine Tune Your Own VITS Model for Free [NanoNomad](https://www.youtube.com/watch?v=6QAGk_rHipE) | | | | | 一键完成Ai声音模拟和音色替换，无需训练模型 – 快速生成AI孙燕姿歌曲 [小薇 Official Channel](https://www.youtube.com/watch?v=YAviCCA-Fic) | | | | | 我们做了个能对话的AI派蒙，免费给大家玩！ [极客湾Geekerwan](https://www.youtube.com/watch?v=8gd_WtBPxaw) | | | | |

变分推断 学习声线 VITS:

Variational Inference with adversarial learning for end-to-end Text-to-Speech

| | | | | Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech | | | | | 【警告】涉及敏感內容！未公開的教學流出！隨時會刪片... #ai孫燕姿 #tuneflow #svs [咖哩哥](https://www.youtube.com/watch?v=EEtQg9zJ0_g) | | | | | TuneFlow [s](https://tuneflow.com/) | | | | | svc-develop-team/[so-vits-svc](https://github.com/svc-develop-team/so-vits-svc) | | | | | 【超火的 AI翻唱】克隆自己的声音！全网最详细的使用教程， So-VITS-SVC 4.1 声音复制神器，完全免费！！ \| [零度解说](https://www.youtube.com/watch?v=o6mKekgJDqw) | | | | | 如何克隆自己的声音？如何克隆别人的声音？免安装1分钟克隆声音 关键还是免费的，支持中文英文日语韩语、AI文字转语音克隆 [峰哥探世界](https://www.youtube.com/watch?v=cli0ZfTxlJA) | | | | | 【GPT-SoVITS 本地整合包0306】声音克隆新纪元！1分钟完美声音克隆，完美复刻任何语音、语调、语气！效果超神！ [十个骑士](https://www.youtube.com/watch?v=J9FwHp9egg0) | | | | | 只需一小时，完美克隆你自己！最新中文AI数字人制作教程, 手机可搞定的AI数字人分身, 中文领域秒杀Heygen数字人 clone yourself perfectly within one hour [靜電的AI設計教室](https://www.youtube.com/watch?v=vBhEuQO2QFc) | | | | |

GPT-SoVITS语音克隆AI，只需一分钟素材训练模型，效果堪比商用。一键安装，附Colab脚本 | TTS | RVC | GPT-SoVITS Colab AI探索与发现

声音克隆 AI探索与发现

| | | | | | | | | | | | | | | | ### Transcribed speech（转录语音） | | | ----------------------------------------------------------------------------------------------------------------------------- | | Transcribed speech 是将口语转录为书面语的过程，也可以理解为将已经存在的音频或视频转换为文本的过程。 | | LeMUR: a framework for applying powerful LLMs to transcribed speech [AssemblyAI](https://www.youtube.com/watch?v=q2RShntLoW0) | | | ## 音乐生成, Text to Music Generation | | | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | MusicLM is a GAMECHANGER for ML Text to Music Generation [Nicholas Renotte](https://www.youtube.com/watch?v=F4WEGvFAwv8) | | Noise2music、MusicLM：文本生成音乐效果如何？ [跟李沐学AI](https://www.youtube.com/watch?v=XsE9WWP9awo) | | "壞了壞了，有了AI音樂人都沒飯吃了！“ [Devin Wang](https://www.youtube.com/watch?v=q8I4NCvmQJ8) | | [AIVA](https://www.aiva.ai/) - The AI composing emotional soundtrack music [v](https://www.youtube.com/watch?v=8wHNIZWIOqg) | | Google's MusicLM: Text Generated Music & It's Absurdly Good [bycloud](https://www.youtube.com/watch?v=2CUKU2iAzAs) | | Music Creation [John Tan Chong Min](https://www.youtube.com/playlist?list=PLcORGO1bTgjWqsb4sEqI9SFUUvLV7HNfh) | | 资深音频人怎么看谷歌最新作曲AI，MusicLM（上集）. How does a composer look at Goolge Music AI MusicLM，Episode I? [Van Zeng \[Audio Man\]](https://www.youtube.com/watch?v=N_s0Tc_Tfa0) | | 资深音频人怎么看谷歌最新作曲AI（下集）读评论，How does a composer look at Goolge Music AI，Episode II, Read Comments [Van Zeng \[Audio Man\]](https://www.youtube.com/watch?v=JBqurD1KG_w) | | 【[Code Gym](https://www.youtube.com/watch?v=0PuslZHJQes)】Python 文字轉語音教學，用短短幾行程式，做出會讀文字說話的自動化服務 | | 借助ChatGPT，乐盲也能轻松驾驭 Google MusicLM，Midjourney来助阵，让音乐与图像完美结合 \| [回到Axton](https://www.youtube.com/watch?v=s3Lm_uff4PA) | | Advanced Music Production with FL Studio – Tutorial [freeCodeCamp](https://www.youtube.com/watch?v=I_ShMaNw0Rc) | | | ### text to song | | | ---------------------------------------------------------------------------------------------------------- | | Voicemod声音模拟 [s](https://tuna.voicemod.net/text-to-song/) [v](https://www.youtube.com/watch?v=YAviCCA-Fic) | | | | | ### X Studio 3 | | | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | X Studio 3 \| 小冰公司AI合成歌声软件 [最佳拍档](https://www.youtube.com/watch?v=GuuDAv0FwxI) [s](https://singer.xiaoice.com/) [doc](https://cpt17i0bkj.feishu.cn/docx/TZOsdaI5xoCunvxptO2ctQXInTg) | | | | | ## 人声分离 | | | ------------------------------------------------------------------------------------------------------------------ | | algoriddim [s](https://www.algoriddim.com/djay-pro-mac) | | vocal remover [v](https://www.youtube.com/watch?v=YAviCCA-Fic) [s](https://www.media.io/online-vocal-remover.html) | | Ultimate Vocal Remover [s](https://ultimatevocalremover.com/) [v](https://www.youtube.com/watch?v=YAviCCA-Fic) | | 除了提取伴奏和人声、还可以提取乐器的免费开源工具! \| Ultimate Vocal Remover \| UVR5 [忙嘞个芒](https://www.youtube.com/watch?v=W7nmoM9OIfE) | | | | | ## Voice Assistant | | | ----------------------------------------------------------------------------------------------------------------------------------------------------- | | Python Voice Assistant [Tech With Tim](https://www.youtube.com/playlist?list=PLzMcBGfZo4-mBungzp4GO4fswxO8wTEFx) | | [search\_query](https://www.youtube.com/results?search_query=Python+Voice+Assistant)=Python+Voice+Assistant | | Azure-Samples/[Cognitive-Services-Voice-Assistant](https://github.com/Azure-Samples/Cognitive-Services-Voice-Assistant) | | Assistente Vocale Python - Riconoscimento Vocale con Speech Recognition e Pyttsx3 [PitoneProgrammatore](https://www.youtube.com/watch?v=kXiIK1qahsg) | | Build an AI Voice Assistant with PyTorch [The A.I. Hacker - Michael Phi](https://www.youtube.com/playlist?list=PL5rWfvZIL-NpFXM9nFr15RmEEh4F4ePZW) | | Build A Python Speech Assistant App [Traversy Media](https://www.youtube.com/watch?v=x8xjj6cR9Nc) | | Intelligent Voice Assistant in Python [NeuralNine](https://www.youtube.com/watch?v=SXsyLdKkKX0) | | Voice Assistant with Wake Word in Python [NeuralNine](https://www.youtube.com/watch?v=F62wb_jfUUw\&list=PL7yh-TELLS1G9mmnBN3ZSY8hYgJ5kBOg-\&index=21) |
Open Jarvis 大數軟體有限公司 \[[Open Jarvis](https://www.youtube.com/watch?v=31DZfkYRvI4)] 如何讓Python 自動將語音轉譯成文字? \[[Open Jarvis](https://www.youtube.com/watch?v=xd_1rn89W2k)] 如何用Python 讓電腦說話? \[[Open Jarvis](https://www.youtube.com/watch?v=Y2t68jDwfhc)] 如何用不到30行Python程式碼寫出「真‧對話機器人」? \[[Open Jarvis](https://www.youtube.com/watch?v=T5UIySP9Owc)] 如何讓對話機器人利用 Wikipedia 回答專業知識? \[[Open Jarvis](https://www.youtube.com/watch?v=9lpoYnWFXjQ)] 如何使用Python寫一個翻譯蒟蒻?