PromtEngineer/Verbi

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1124 stars · 217 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Verbi is a modular Python voice assistant application for experimenting with state-of-the-art transcription, LLM response generation, and text-to-speech models. It integrates OpenAI, Groq, Deepgram, ElevenLabs, and Cartesia APIs, plus local models via Ollama and Piper.

Use cases

• build a voice assistant with swappable STT and TTS models
• compare transcription models like Whisper vs Deepgram
• experiment with local LLMs via Ollama for voice responses
• prototype a speech-to-speech pipeline in Python
• benchmark TTS providers like ElevenLabs and Cartesia
• research modular voice assistant architectures

When to choose

• you want to mix and match SOTA speech and LLM models in one pipeline
• you need a Python codebase for voice assistant research and experimentation
• you want both cloud APIs and local model support

When to avoid

• you need a production-ready, polished consumer voice assistant
• you want a no-code or GUI-only solution
• you need low-latency streaming voice interaction out of the box

Facets

application · maturity active

speech-recognition tts llm-inference chatbot audio-processing artificial-intelligence speech-processing developer-tools python cross-platform voice-assistant transcription text-to-speech ollama modular research natural-language-processing

Member repositories

For agents

markdown · JSON · MCP: product_card(name="PromtEngineer/Verbi")