MatteoFasulo/Whisper-TikTok

From AI tools to TikTok video creation using FFMPEG, Microsoft Edge read aloud and OpenAI Whisper model

What it solves

Whisper-TikTok automates the creation of engaging TikTok videos by combining transcription, voiceover, and visual assembly. It eliminates the need for manual subtitling and the use of robotic-sounding AI voices, providing a more natural auditory experience.

How it works

The tool integrates three core technologies:

  1. OpenAI-Whisper (via stable-ts) to generate accurate transcriptions from audio files.
  2. Microsoft Edge Cloud TTS API to create high-quality, natural-sounding voiceovers.
  3. FFMPEG to assemble the final video, including the application of subtitles and background visuals.

Who it’s for

Content creators who want to quickly generate TikTok-style videos with accurate captions and high-quality AI voiceovers without manually editing each clip.

Highlights

  • Natural Voiceovers: Uses Edge TTS for a more authentic sound than typical TikTok AI voices.
  • Customizable Subtitles: Allows users to adjust font size, color, and position.
  • Harnesses YouTube: Supports using YouTube URLs as background video sources.
  • Flexible CLI: Provides a wide range of command-line options for voice selection, language, and styling.

Related

  • Project
    Asad-Ismail/MoneyPrinterTurbo-Extended

    An automated video generation tool that creates scripts, synthesizes voiceovers with local voice cloning, and matches relevant video clips with synchronized word-level subtitles.

  • Project
    naqashafzal/AI-Content-Studio

    AI Content Studio is an open‑source platform that automates the whole video‑creation workflow. A supervisory set of AI agents researches a topic, writes and QA‑checks a script, then a multimodal pipeline (Whisper transcription, OpenCV scene analysis, FFmpeg processing) produces a fully‑styled, loudness‑normalized video with captions, B‑roll and branding. It supports style‑cloning from reference clips, Urdu TTS, and 24/7 auto‑pilot campaigns, and runs via a FastAPI backend + Next.js UI.

  • Project
    leamsigc/ShortsGenerator

    ShortsGenerator is an open‑source tool that automates the creation of YouTube Shorts: AI‑written scripts, stock‑video download, multi‑voice TTS (including local Qwen‑3), subtitles, music, image stitching, and scheduling to social platforms via MagicSync. It ships a Flask backend (Python 3.11) and a Nuxt 3 UI, runs locally or via Docker, and targets creators/agencies needing a repeatable short‑form video pipeline.

  • Project
    wendy7756/AI-Video-Transcriber

    An AI-powered tool to transcribe, summarize, and archive videos and podcasts from 30+ platforms or local files using Faster-Whisper and LLMs.