Real-Time-Voice-Cloning
mimic-recording-studio
Our great sponsors
Real-Time-Voice-Cloning | mimic-recording-studio | |
---|---|---|
96 | 4 | |
50,738 | 486 | |
- | 1.2% | |
0.0 | 0.0 | |
about 1 month ago | 12 months ago | |
Python | JavaScript | |
GNU General Public License v3.0 or later | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Real-Time-Voice-Cloning
- FLaNK Stack Weekly 12 February 2024
- Voice Cloning
- Show HN: Real Time Voice Cloning – Instant DeepFake Audio
- Bu dakikadaki bahsedilen yapay zekayı bulamadım yardımcı olur musunuz?
- Alarming Rise of Voice Cloning Fraud Targeting the Elderly through AI
- Dark Brandon going hard
- Conselho do TRF-4 afasta juiz da Lava Jato
-
What Photoshop Can't Do, DragGAN Can! See How! Paper Explained, Along with Additional Supplementary Video Footage
Oh maybe it is available: https://github.com/CorentinJ/Real-Time-Voice-Cloning
-
Regarding recent posts about AI voice generation
I know this isn't the bulk of your argument, but if the concern is uploading, offline voice cloners have existed for years (albeit not as good as elevenlabs) but will presumably get far better in the years to come now that everyone has seen what's possible and as PC compute power continues to improve. https://github.com/CorentinJ/Real-Time-Voice-Cloning
- 'He Would Still Be Here': Man Dies by Suicide After Talking with AI Chatbot, Widow Says | The incident raises concerns about guardrails around quickly-proliferating conversational AI models.
mimic-recording-studio
-
How can I create a dataset to refine Whisper AI from old videos with subtitles?
I weirdly can't find a great off-the-shelf app for this. l'd love to know if anyone finds one. Most stuff seems to be for recording data for Text To Speech (going the other way). Mimic Recording Studio looks the best. Then there's speech training recorder and TTS Dataset Creator (video). You don't have to worry about audio quality as much as they do.
-
Experts warn people not to put Amazon Echo Alexa devices in their bedrooms
If you genuinely want to help out in that way, you can create a voice for Mycroft using their Mimic recording studio software. They reckon it takes about 40-80 hours all up.
-
Mimic 3 by Mycroft
They want you to make good quality audio recordings of you speaking about 20 000 phrases. It could take 40 to 80 hours of speaking and recording, maximum 4 hours per day.
https://github.com/MycroftAI/mimic-recording-studio
https://mycroft.ai/contribute/
- How can I immortalise my dying mums voice in some sort of voice assistant?
What are some alternatives?
TTS - 🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
annyang - :speech_balloon: Speech recognition for your site
DeepFaceLab - DeepFaceLab is the leading software for creating deepfakes.
google-tts - Google TTS (Text-To-Speech) for node.js
tortoise-tts - A multi-voice TTS system trained with an emphasis on quality
speaker.app - Speaker.app (https://speaker.app) is an encrypted peer-to-peer (P2P) group communication platform which does not require a user account to use. Users remain anonymous on the network unless choosing to personally identify themselves.
MockingBird - 🚀AI拟声: 5秒内克隆您的声音并生成任意语音内容 Clone a voice in 5 seconds to generate arbitrary speech in real-time
mimic3 - A fast local neural text to speech engine for Mycroft
silero-models - Silero Models: pre-trained speech-to-text, text-to-speech and text-enhancement models made embarrassingly simple
Portainer - Making Docker and Kubernetes management easy.
glados-voice-assistant - DIY Voice Assistant based on the GLaDOS character from Portal video game series. Works with home assistant!
Appwrite - Build like a team of hundreds_