a developer to create an automatic transcription + subtitle file generation tool for TikTok, Instagram Reels, and YouTube Shorts videos
Budget: $5,000 – $10,000 USD
Job Posting (Tool Development)
Overview
We are Creative Sense, a Japan-based company working with major partners such as SoftBank and Microsoft.
We are looking for a developer to create an automatic transcription + subtitle file generation tool for TikTok, Instagram Reels, and YouTube Shorts videos.
The tool should allow users to:
Upload a video
Automatically transcribe Japanese audio with high accuracy
Output subtitle files (.srt / .vtt)
Required Features
Support for uploading video files (MP4, MOV, etc.)
Automatic transcription of Japanese audio (high accuracy)
Subtitle file output (.srt or .vtt)
Automatic timestamp generation
Usable either as a web-based tool or a local application
Nice-to-Have Features
Simple editor UI for manual correction of transcription errors (web-based)
Multi-language support (Japanese + English, etc.)
API integration (e.g., automatically process uploaded videos and return results)
Utilization of open-source speech recognition models (e.g., Whisper)
Timeline
MVP delivery within 4–6 weeks after contract signing
Additional features can be discussed and implemented step by step
Budget
Around USD 5,000 (including taxes and platform fees)
Flexible depending on final feature scope
Requirements
Experience in application development with Python / Node.js
Familiarity with speech recognition APIs (Whisper, Vosk, Google Speech-to-Text, etc.)
Comfortable with project management using GitHub (or similar tools)
Preferred Skills
Frontend development (React / Next.js)
Understanding of video editing and social media operations
Experience deploying with Docker or on cloud platforms (GCP/AWS)
Deliverables
GitHub repository or deployed environment on a cloud platform
Basic usage manual / README
How to Apply
Share past development experience and portfolio
Propose a preferred tech stack (e.g., Whisper + FastAPI + React)
Provide an estimated development schedule
Overview
We are Creative Sense, a Japan-based company working with major partners such as SoftBank and Microsoft.
We are looking for a developer to create an automatic transcription + subtitle file generation tool for TikTok, Instagram Reels, and YouTube Shorts videos.
The tool should allow users to:
Upload a video
Automatically transcribe Japanese audio with high accuracy
Output subtitle files (.srt / .vtt)
Required Features
Support for uploading video files (MP4, MOV, etc.)
Automatic transcription of Japanese audio (high accuracy)
Subtitle file output (.srt or .vtt)
Automatic timestamp generation
Usable either as a web-based tool or a local application
Nice-to-Have Features
Simple editor UI for manual correction of transcription errors (web-based)
Multi-language support (Japanese + English, etc.)
API integration (e.g., automatically process uploaded videos and return results)
Utilization of open-source speech recognition models (e.g., Whisper)
Timeline
MVP delivery within 4–6 weeks after contract signing
Additional features can be discussed and implemented step by step
Budget
Around USD 5,000 (including taxes and platform fees)
Flexible depending on final feature scope
Requirements
Experience in application development with Python / Node.js
Familiarity with speech recognition APIs (Whisper, Vosk, Google Speech-to-Text, etc.)
Comfortable with project management using GitHub (or similar tools)
Preferred Skills
Frontend development (React / Next.js)
Understanding of video editing and social media operations
Experience deploying with Docker or on cloud platforms (GCP/AWS)
Deliverables
GitHub repository or deployed environment on a cloud platform
Basic usage manual / README
How to Apply
Share past development experience and portfolio
Propose a preferred tech stack (e.g., Whisper + FastAPI + React)
Provide an estimated development schedule