# PromtEngineer/Verbi

A modular voice assistant application for experimenting with state-of-the-art transcription, response generation, and text-to-speech models. Supports OpenAI, Groq, Elevanlabs, CartesiaAI, and Deepgram APIs, plus local models via Ollama. Ideal for research and development in voice technology.

Repository: https://github.com/PromtEngineer/Verbi
Canonical: https://ross.abutalabs.com/products/verbi
Language: Python
License: MIT
License Family: permissive
Last push: 2025-11-22T07:08:26+00:00

## Health v2 (maintenance only)
Score: 48/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 53, release rhythm 35, longevity 59
- inputs: {"age_days": 835, "days_push": 284, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1124, forks 217 (observed 2026-08-28T04:03:40.822251+00:00)

## What it is
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
- artifact type: application
- maturity: active
- function: speech-recognition, tts, llm-inference, chatbot, audio-processing
- domain: artificial-intelligence, speech-processing, developer-tools
- platform: python, cross-platform
- tags: voice-assistant, transcription, text-to-speech, ollama, modular, research, natural-language-processing

## Member repositories
- PromtEngineer/Verbi (main) score 48

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:40.822251+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:39:37.478022+00:00, confidence not recorded.
  - readme: https://github.com/PromtEngineer/Verbi (fetched 2026-08-28T04:03:40.822251+00:00, sha 47a98b14e5c9)
- Data as of 2026-08-30T08:39:29.467469+00:00.