ScrAIbe – LocalAI-Backed Transcription and Summarization

ScrAIbe is a lightweight transcription and summarization client that:

• Sends audio to a LocalAI server running vibevoice.cpp for transcription and speaker diarization.
• Optionally uses a second LLM to generate a detailed, structured summary of the conversation.

No local speech models or heavy dependencies are required. ScrAIbe is designed to be run as a thin client in front of your own AI services.

Features

• Transcription with speaker diarization via LocalAI:
  • Uses the /v1/audio/diarization endpoint.
  • Compatible with vibevoice.cpp and other diarization-capable backends.
• Optional AI-powered summarization:
  • Task: transcript_and_summarize
  • Chunks long transcripts, summarizes each chunk, then generates a final comprehensive summary.
  • Summary highlights:
    • Main topics and discussion points
    • Key decisions and outcomes
    • Action items and responsibilities
    • Open issues and risks
• CLI and Python API:
  • Simple command-line interface.
  • Drop-in Scraibe class for integration into other tools.
• Docker-ready:
  • Lightweight container, configured via environment variables.

Architecture

• LocalAI (vibevoice.cpp):
  • Handles audio → transcript + speaker segments.
• Summarizer LLM (OpenAI-compatible chat endpoint):
  • Handles transcript → structured summary.
• ScrAIbe:
  • Orchestrates:
    • File upload to LocalAI
    • Transcript assembly
    • Chunked summarization
    • Output formatting (e.g., .md with transcript + summary)

Quick Start (CLI)

Basic usage:

• Transcribe:

  • python3 -m scraibe.cli -f "audio.wav" -o "./output" -of txt

• Transcribe and summarize:

  • python3 -m scraibe.cli -f "audio.wav" -o "./output" --task transcript_and_summarize

Environment variables must be set to point to your LocalAI and summarizer LLM.

Python API

Example: transcribe only

• from scraibe import Scraibe

  • client = Scraibe()
  • text = client.transcribe("audio.wav")
  • print(text)

Example: transcribe and summarize

• from scraibe import Scraibe

  • client = Scraibe()
  • result = client.transcript_and_summarize("audio.wav")
  • transcript = result["transcript"]
  • summary = result["summary"]

You can override endpoints and models via environment variables or constructor parameters if needed.

Command-Line Options

Run:

• python3 -m scraibe.cli -h

Key options:

• -f / --audio-files:
  • One or more audio files to process.
• --task:
  • transcribe (default)
  • transcript_and_summarize
• -o / --output-directory:
  • Output folder for generated files.
• -of / --output-format:
  • txt, json, md, html
  • For transcript_and_summarize, output is always saved as .md with:

    • Transcript

    • Summary

Other options (e.g., --language, --num-speakers) are accepted and forwarded where applicable; many legacy Whisper/Pyannote flags are kept for compatibility but ignored.

Docker Usage

ScrAIbe is designed to run in Docker as a client to your LocalAI and summarizer LLM.

Basic run (transcribe)

• docker run -it
  -e LOCALAI_API_URL=http://localai:8080
  -v /path/to/audio:/audio
  scraibe:latest
  -f /audio/meeting.wav -o /audio/output -of txt

Basic run (transcribe + summarize)

• docker run -it
  -e LOCALAI_API_URL=http://localai:8080
  -e SUMMARIZER_API_URL=http://llm:8080
  -v /path/to/audio:/audio
  scraibe:latest
  -f /audio/meeting.wav -o /audio/output --task transcript_and_summarize

Docker Environment Variables

The following environment variables configure ScrAIbe in Docker.

Transcription / Diarization (LocalAI):

• LOCALAI_API_URL:
  • Required.
  • Base URL of the LocalAI server.
  • Example: http://localai:8080
• LOCALAI_API_KEY:
  • Optional.
  • API key for LocalAI, if configured.
• LOCALAI_MODEL:
  • Optional (default: vibevoice-diarize).
  • Model name used for transcription/diarization.

Summarization LLM:

• SUMMARIZER_API_URL:
  • Required when using --task transcript_and_summarize.
  • Base URL of the summarization LLM (OpenAI-compatible /v1/chat/completions).
  • Example: http://llm:8080
• SUMMARIZER_API_KEY:
  • Optional.
  • API key for the summarization LLM, if required.
• SUMMARIZER_MODEL:
  • Optional (default: llama-3.1-8b-instruct).
  • Model name used for summarization.

All of these can also be overridden from the CLI when needed (e.g., --localai-api-url, --summarizer-api-url).

Dependencies

Core runtime dependencies:

• Python 3.9+
• httpx
• numpy
• tqdm
• ffmpeg (for audio preprocessing)

No local Whisper, PyTorch, or Pyannote models are required.

Contributing

Contributions are welcome. Please refer to CONTRIBUTING.md for guidelines.

License

This project is licensed under GPL-3.0. See LICENSE for details.