https://github.com/thorwebdev/webcam-audio-description-ai
Capture webcam via browser, generate text descriptions with Google Gemini, generate speech with ElevenLabs
https://github.com/thorwebdev/webcam-audio-description-ai
elevenlabs elevenlabs-api gemini gemini-api wcag2
Last synced: 10 months ago
JSON representation
Capture webcam via browser, generate text descriptions with Google Gemini, generate speech with ElevenLabs
- Host: GitHub
- URL: https://github.com/thorwebdev/webcam-audio-description-ai
- Owner: thorwebdev
- Created: 2024-10-16T09:10:12.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-11-13T03:01:22.000Z (over 1 year ago)
- Last Synced: 2024-12-19T10:12:38.629Z (over 1 year ago)
- Topics: elevenlabs, elevenlabs-api, gemini, gemini-api, wcag2
- Language: TypeScript
- Homepage:
- Size: 16.6 KB
- Stars: 27
- Watchers: 2
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Webcam Audio Description Generator
Generate audio descriptions for your videos using [Google Gemini]() and [ElevenLabs]().
## Setup
- `cp supabase/functions/.env. example supabase/functions/.env`
- Set your [Gemini API key](https://ai.google.dev/gemini-api/docs/api-key) in `supabase/functions/.env`
- Set your [ElevenLabs API key](elevenlabs.io/?from=partnersmith6824) in `supabase/functions/.env`
## Run locally
```bash
supabase start
supabase functions serve --no-verify-jwt
# In another terminal
python3 -m http.server
```
Open http://localhost:8000/