StreamStory

StreamStory is a self-reported tool built for talent agencies managing gaming livestream creators. The author states it automates campaign reporting by processing Twitch VODs into editable Google Docs with timestamps, analytics, and insights. It uses local GPU transcription (faster-whisper), GPT-5.6 Terra for analysis, and integrates with Twitch and Google Docs.

The project is described as a hackathon submission with no evidence of revenue, customers or traction beyond the author’s own testing. The team size is two, and the tool is built using a mix of open-source and proprietary technologies including Codex, CUDA, FastAPI, React, and GPT-5.6 Terra.

The description states that StreamStory turns Twitch VODs into creator-forward campaign reports, using local GPU transcription and GPT-5.6 Terra for analysis.

It is described as a tool that:

• Downloads audio from Twitch VODs
• Uses FFmpeg to prepare the audio
• Transcribes with faster-whisper on a local GPU
• Allows staff to search transcripts, confirm sponsored sections, upload analytics, and add multiple creators over several days
• Generates an editable Google Doc containing:
  • Campaign recap
  • Timestamped Twitch moments
  • Activation insights
  • Creator and campaign analytics

Inference The tool is built for talent agencies managing livestream creators and aims to reduce manual effort in reporting.

The author states that StreamStory was built to save time spent scrubbing through VODs, replacing hours of manual work with a report that "actually showcases the creators’ work."

It positions itself as a solution for:

• Talent managers handling campaign reporting
• Reducing tedious, time-consuming tasks in livestream sponsorships
• Improving sponsor visibility into creator performance

Inference The tool is positioned as a time-saving automation tool for agencies managing multiple creators and sponsorships.

The description states that the author runs a talent agency for gaming livestream creators, and that the tool was built to help with campaign reporting in this context.

It is implied that the target customer is:

• Talent agencies or managers
• Organizations that work with gaming livestream creators
• Teams that need to generate reports from long VODs

Inference The ICP appears to be talent agencies or internal teams managing creator sponsorships, but no specific customer segments or personas are defined.

The description does not state anything about pricing, monetization, or a business model. It is self-reported as a hackathon project with no evidence of revenue streams or commercial use beyond the author’s own testing.

Not evidenced

The tool is built using:

• Frontend: React, TypeScript, Vite
• Backend: FastAPI, Python
• Database: SQLite
• Transcription: faster-whisper (local GPU)
• AI/ML: GPT-5.6 Terra
• Other tools: FFmpeg, Codex, node.js, CUDA, Twitch API, Google Docs API

The author states that the tool was built in a hackathon environment using real VODs and campaign data.

Inference The technical stack suggests a developer-focused, local-GPU-based solution with integration into Twitch and Google Docs. It is not clear if it’s designed for scalability or cloud deployment.

The description states that the tool was built as a hackathon submission, and that it was tested using real multi-creator campaign data.

It includes:

• Full workflow testing
• Iteration with real VODs, screenshots, terminal errors, transcripts, and campaign reports
• A reporting standard developed through testing

Not evidenced No evidence of adoption, customers, or revenue. The tool is described as a prototype, not a product in use.

The description does not mention any competitors or existing tools in the space. It is self-reported as a solution for campaign reporting in livestreaming, but no comparison to other tools or platforms is made.

Not evidenced

• No traction: The tool is described only as a hackathon project with no evidence of adoption or usage beyond the author’s own testing.
• Unproven market fit: No evidence that talent agencies or creators are interested in this solution.
• Limited scalability: Built for local GPU transcription and manual workflows, not designed for enterprise use.
• Unverified claims: The tool is described as replacing hours of manual work, but no data supports this.
• No commercialization path: No pricing, monetization or go-to-market strategy is evident.

1. What specific talent agencies or teams are using StreamStory beyond the author’s own testing?
2. How does the tool handle VODs that are not in the correct format or have audio issues?
3. Has the team considered how to scale this solution for enterprise use or multiple clients?
4. Is there any feedback from creators or sponsors on the utility of the generated reports?
5. What is the current plan for monetization or product development beyond the hackathon?