AlexandreSajus/JARVIS
Your own personal voice assistant: Voice to Text to LLM to Speech, displayed in a web interface
Chains Deepgram (speech-to-text), OpenAI GPT-3 (response generation), and ElevenLabs (text-to-speech) APIs into a unified pipeline with real-time conversation logging. The architecture separates concerns across two processes—a Taipy web frontend displaying the conversation history and a CLI backend handling the voice I/O loop with Pygame audio playback. Requires API keys for all three services and runs on Python 3.8-3.11.
515 stars. No commits in the last 6 months.
Stars
515
Forks
100
Language
Python
License
GPL-3.0
Category
Last pushed
Jun 09, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/AlexandreSajus/JARVIS"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
jenswittmann/CurlyFramework
Tiny Framework for accessibility and sustainability, not only for MODX or Kirby CMS.
rodrigosuelli/ditey-web
🎙 Leitor de textos online desenvolvido com React e Web Speech API. Tcc (ETEC)
douglasmendescwb/prefeitura
Sistema completo de acessibilidade web com ajuste de fontes, modo escuro, alto contraste e...
dayvidwhy/quick-glance
⚡ Swiftly access key notes efficiently whenever, wherever you need. Uses Tailwind and Angular.