Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
AI Vtuber for Streaming on Youtube/Twitch
| Date | Stars |
|---|---|
| 2026-07-24 | 1104 |
| 2026-07-25 | 1104 |
| 2026-07-28 | 1105 |
| 2026-07-30 | 1105 |
| 2026-08-06 | 1105 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# AI Waifu Vtuber & Assistant An AI waifu virtual YouTuber that hears your voice, replies in character, and talks back with text-to-speech. It can also read Twitch chat and answer your viewers. This project is inspired by shioridotdev and uses VoiceVox Engine, DeepL, Whisper OpenAI, Seliro TTS, and VtubeStudio.  ## Update v3.5 Now it also supports for Twitch Streamer v3.0 Now not only supports Japanese TTS using VoiceVox. But also supports TTS for RU (Russian), EN (English), DE (German), ES (Spanish), FR (French), TT (Tatar), UA (Ukrainian), UZ (Uzbek), XAL (Kalmyk), Indic (Hindi), using Seliro TTS. Change `voicevox_tts` on `run.py` to `seliro_tts`, for detailed information of how to use [Seliro TTS](https://github.com/snakers4/silero-models#text-to-speech) ## Demo - [Demo](https://www.youtube.com/shorts/_mKVr3ZaM9Q) - [Live Test](https://youtu.be/h6UEgJxH1-E?t=1616) - [Code Explain](https://youtu.be/qpNG9qrcmrQ) - [Clip](https://www.youtube.com/watch?v=qTkESIBd5Qk) ## Technologies Used - [VoiceVox Docker](https://hub.docker.com/r/voicevox/voicevox_engine) or [](https://colab.research.google.com/github/SociallyIneptWeeb/LanguageLeapAI/blob/main/src/run_voicevox_colab.ipynb) - [DeepL](https://www.deepl.com/fr/account/summary) - [Deeplx](https://github.com/OwO-Network/DeepLX) - [Whisper OpenAI](https://platform.openai.com/account/api-keys) - [Seliro TTS](https://github.com/snakers4/silero-models#text-to-speech) - [VB-Cable](https://vb-audio.com/Cable/) - VtubeStudio ## Installation 1. Install the dependencies ``` pip install -r requirements.txt ``` 2. Create config.py and store your Openai API key ``` api_key = 'yourapikey' ``` 3. Change the owner name ``` owner_name = "Ardha" ``` If you want to use it for livestream, create a list of users that you want to blacklist on `run.py` ``` blacklist = ["Nightbot", "streamelements"] ``` 4. Change the lore or identity of your assistant. Edit the txt file at `characterConfig\Pina\identity.txt` 5. If you want to stream on Twitch, change the config file at `utils/twitch_config.py`. Get your token from [here](https://twitchapps.com/tmi/). Your token should look something like oauth:43rip6j6fgio8n5xly1oum1lph8ikl1 (fake for this tutorial). After you change the config file, start the program using Mode - 3. ``` server = 'irc.chat.twitch.tv' port = 6667 nickname = 'testing' # You don't need to change this token = 'oauth:43rip6j6fgio8n5xly1oum1lph8ikl1' # get it from https://twitchapps.com/tmi/. user = 'ardha27' # Your Twitch username channel = '#aikohound' # The channel you want to retrieve messages from ``` 6. Choose which TTS you want to use, `VoiceVox` or `Silero`. Uncomment and comment to switch between them. ``` # Choose between the available TTS engines # Japanese TTS voicevox_tts(tts) # Silero TTS, Silero TTS can generate English, Russian, French, Hindi, Spanish, German, etc. Uncomment the line below. Make sure the input is in that language # silero_tts(tts_en, "en", "v3_en", "en_21") ``` To use VoiceVox, run the VoiceVox Engine first. You can run it locally with [VoiceVox Docker](https://hub.docker.com/r/voicevox/voicevox_engine), or on Google Colab with [VoiceVox Colab](https://github.com/SociallyIneptWeeb/LanguageLeapAI/blob/main/src/run_voicevox_colab.ipynb). If you use the Colab one, change `voicevox_url` on `utils\TTS.py` to the link you get from Colab. ``` voicevox_url = 'http://localhost:50021' ``` To see the VoiceVox voice list, check [VoiceVox](https://voicevox.hiroshiba.jp), find the speaker id in `speaker.json`, then change it on `utils/TTS.py`. For Seliro voice samples, check [Seliro Samples](https://oobabooga.github.io/silero-samples/index.html). 7. Choose which translator you want to use based on your use case (optional, only if you need translation for the answers). Pick
Excerpt of 7,564 characters
Read on GitHub
46
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:6c9a6f5b5c41c41e, topic:speech-recognition, topic:tts, topic:whisper