PraisonAI Editor

AI-powered audio & video editor for PraisonAI. Protocol-driven, modular, and ready for agent integration.

Install

pip install praisonai-editor

With local Whisper support:

pip install "praisonai-editor[local]"

With PraisonAI Agent integration:

pip install "praisonai-editor[agent]"

Quick Start

CLI

# Edit audio (transcribe → detect fillers/silence → render)
praisonai-editor edit podcast.mp3 --preset podcast --verbose

# Edit video
praisonai-editor edit interview.mp4 --output edited.mp4

# AI-guided editing with prompt
praisonai-editor edit podcast.mp3 --prompt "Remove intro and off-topic weather discussion"

# Transcribe
praisonai-editor transcribe audio.mp3 --format srt

# Convert MP4 → MP3
praisonai-editor convert video.mp4 --format mp3

# Probe file metadata
praisonai-editor probe media.mp4

Python API

from praisonai_editor import edit_media, transcribe_audio, convert_media

# Edit any media
result = edit_media("podcast.mp3", preset="podcast")

# Transcribe
transcript = transcribe_audio("audio.mp3")
print(transcript.to_srt())

# Convert
convert_media("video.mp4", "audio.mp3")

PraisonAI Agent

from praisonaiagents import Agent
from praisonai_editor.agent_tool import audio_editor_tool

agent = Agent(
    instructions="You are an audio editor.",
    tools=[audio_editor_tool],
)

Presets

Requirements

• Python ≥ 3.10
• FFmpeg (for audio/video processing)
• OpenAI API key (for transcription) or [local] extra for offline Whisper