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.
From AI tools to TikTok video creation using FFMPEG, Microsoft Edge read aloud and OpenAI Whisper model
| Date | Stars |
|---|---|
| 2026-07-24 | 337 |
| 2026-07-25 | 337 |
| 2026-07-28 | 338 |
| 2026-07-30 | 338 |
| 2026-08-06 | 338 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Introducing Whisper-TikTok 🤖🎥 ## Star History [](https://www.star-history.com/) ## Table of Contents - [Introduction](#introduction) - [Installation](#installation-️) - [Command-Line](#command-line) - [Usage Examples](#usage-examples) - [Additional Resources](#additional-resources) - [Code of Conduct](#code-of-conduct) - [Contributing](#contributing) - [Acknowledgments](#acknowledgments) - [License](#license) ## Introduction Discover Whisper-TikTok, an innovative AI-powered tool that leverages the prowess of **Edge TTS**, **OpenAI-Whisper**, and **FFMPEG** to craft captivating TikTok videos. Harnessing the capabilities of OpenAI's Whisper model, Whisper-TikTok effortlessly generates an accurate **transcription** from provided audio files, laying the foundation for the creation of mesmerizing TikTok videos through the utilization of **FFMPEG**. Additionally, the program seamlessly integrates the **Microsoft Edge Cloud Text-to-Speech (TTS) API** to lend a vibrant **voiceover** to the video. Opting for Microsoft Edge Cloud TTS API's voiceover is a deliberate choice, as it delivers a remarkably **natural and authentic** auditory experience, setting it apart from the often monotonous and artificial voiceovers prevalent in numerous TikTok videos. ### Demo Video <https://github.com/MatteoFasulo/Whisper-TikTok/assets/74818541/68e25504-c305-4144-bd39-c9acc218c3a4> ## Installation 🛠️ Whisper-TikTok has been tested in Windows 10, Windows 11 and Ubuntu 24.04 systems equipped with **Python versions 3.11, and 3.12**. If you want to run Whisper-TikTok locally, you can clone the repository using the following command: ```bash git clone https://github.com/MatteoFasulo/Whisper-TikTok.git ``` Install the required dependencies using pip: ```python pip install -r requirements.txt ``` However, we encourage the adoption of astral [`uv`](https://docs.astral.sh/uv/) to install the required dependencies. If you are using `uv`, you can install the dependencies with the following command: ```bash uv pip install -e . --torch-backend=auto ``` >Note: The `--torch-backend=auto` allows automatic selection of the appropriate PyTorch backend. More info can be found in the [uv documentation](https://docs.astral.sh/uv/guides/integration/pytorch/#automatic-backend-selection). ### FFMPEG Installation Binaries for [**FFMPEG**](https://ffmpeg.org/) are not included in the repository and must be installed separately. Make sure to have FFMPEG installed and accessible in your system's PATH. For convenience, here are the installation instructions for various package managers: ```bash # on Ubuntu or Debian sudo apt update && sudo apt install ffmpeg # on Arch Linux sudo pacman -S ffmpeg # on MacOS using Homebrew (<https://brew.sh/>) brew install ffmpeg # on Windows using Chocolatey (<https://chocolatey.org/>) choco install ffmpeg # on Windows using Scoop (<https://scoop.sh/>) scoop install ffmpeg ``` ## Command-Line To run the program from the command-line, execute the following command within your terminal: ```bash whisper_tiktok --help ``` which will provide you with a list of available commands. ### CLI Options Whisper-TikTok supports many command-line options to customize the generated TikTok video. Just to name a few, you can choose the Whisper model to use, the TTS voice, subtitle format, subtitle position, font size, font color, and many more. To browse all available options, run the following command: ```bash whisper_tiktok create --help ``` > If you use the --random_voice option, please specify both --gender and --language arguments. Whisper model will auto-detect the language of the audio file and use the correspond
Excerpt of 5,926 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:ea5cadc5ef468ce3, topic:text-to-speech, topic:whisper, readme:text-to-speech