AI Helpers
June 2026
Since April 2024
Introduction
AI Helpers is a suite of 10 Python libraries, licensed under BSD-3-Clause (same as scikit-learn / numpy / scipy), designed to simplify AI development across audio/video processing, live speech and text-to-speech, media acquisition, capture, and secure storage. The suite is organized into groups, so you install only the corner you need: Core (OS Helper), Audio & voice (Audio, Vocal, Speaker), Video & capture (Video, Capture), Media acquisition (YouTube, Podcast), and Storage & transfer (Bucket, SFTP). Whether you're handling media files, transcribing and diarizing conversations, synthesizing speech, scraping creator engagement metadata, streaming podcasts to PCM for ASR, capturing camera/microphone/screen inputs, or managing secure transfers and object storage, AI Helpers streamlines repetitive tasks so you can focus on building.
Install just the group you need via the
ai-helpers meta-package,
which exposes each group as an extra. The base install is light (just os-helper) —
add the group(s) you want, or [all] for the kitchen sink:
# 🔊 Audio & voice
pip install "ai-helpers[audio] @ git+https://github.com/warith-harchaoui/ai-helpers.git@v0.2.0"
# 🎬 Video & capture
pip install "ai-helpers[video] @ git+https://github.com/warith-harchaoui/ai-helpers.git@v0.2.0"
# 🌐 Media acquisition
pip install "ai-helpers[acquire] @ git+https://github.com/warith-harchaoui/ai-helpers.git@v0.2.0"
# 🗄️ Storage & transfer
pip install "ai-helpers[storage] @ git+https://github.com/warith-harchaoui/ai-helpers.git@v0.2.0"
# 🧰 several groups at once, or everything
pip install "ai-helpers[audio,video] @ git+https://github.com/warith-harchaoui/ai-helpers.git@v0.2.0"
pip install "ai-helpers[all] @ git+https://github.com/warith-harchaoui/ai-helpers.git@v0.2.0"
Each helper is also its own package. Those already on PyPI install by name —
pip install os-helper audio-helper capture-helper bucket-helper — and the
rest are landing on PyPI progressively; until then the meta-package above pulls them
in at pinned versions automatically. You can also grab any single helper straight from
GitHub, e.g. pip install "vocal-helper @ git+https://github.com/warith-harchaoui/vocal-helper.git@v0.3.7".
You still need ffmpeg on PATH for the media helpers (audio / video / youtube / podcast / capture / vocal) — brew install ffmpeg on macOS 🍎.
Contents
- Introduction
- 🧱 Core
- 🔊 Audio & voice
- 🎬 Video & capture
- 🌐 Media acquisition
- 🗄️ Storage & transfer
- 🧩 Standalone tools (not bundled)
🧱 Core
OS Helper
OS Helper is a Python library that provides utility functions for working with different operating systems. It offers a set of tools to simplify common system operations, file handling, hashing, config and timing — the shared foundation every other helper builds on.
🍏 OS Helper
🔊 Audio & voice
Audio Helper
Audio Helper is a Python library that provides utility functions for processing audio files. It includes features like loading audio, converting formats, separating audio sources (optional Demucs), and splitting and concatenating audio files.
🔈 Audio Helper
Vocal Helper
Vocal Helper is a Python library that turns audio into diarized, transcribed utterances — and optionally a rolling LLM summary of the conversation. It runs as an async producer/consumer pipeline in two modes: online streaming (live PCM to live transcript) and offline batch (full audio buffer for highest-quality analysis), chaining voice activity detection, speaker diarization, speech-to-text and optional summarization. Built on Silero VAD, whisper.cpp, pyannote / NeMo diarization backends and Ollama-served language models, it exposes CLI, Python, HTTP and MCP interfaces for live meetings, podcasts and voicemail processing.
🗣️ Vocal Helper
Speaker Helper
Speaker Helper is the inverse of Vocal Helper: offline and streaming text-to-speech over a local TTS engine, with voice cloning from a short reference sample. Text-in → speech-out, low-latency for live narration or batch for highest quality — closing the loop from speech understanding (Vocal) back to speech synthesis.
🔊 Speaker Helper
🎬 Video & capture
Video Helper
Video Helper is a Python library that provides utility functions for processing video files: multi-backend frame extraction (VidGear / PyAV / ffmpeg-pipe), loading, converting, and working with subtitle formats.
📺 Video Helper
Capture Helper
Capture Helper is the OBS-inspired input + processing + publishing layer for the AI Helpers stack. Library-shaped (no GUI): cross-platform camera / microphone / screen / window capture, composable filter chains (noise gate, gain, chroma key, scale), multi-source mixing, and emit-to-publish primitives for live YouTube / Twitch RTMP, HLS, and Icecast (live podcasts). It plugs into video-helper and podcast-helper for the same downstream PCM and frame contracts.
🎥 Capture Helper
🌐 Media acquisition
YouTube Helper
YouTube Helper is a Python library that provides utility functions for downloading videos, audio, and thumbnails from platforms like YouTube, Vimeo, DailyMotion, SoundCloud and Twitch using yt-dlp. It also supports post-processing tasks such as converting or merging media files with ffmpeg, browsing video stream catalogs, and pulling no-API engagement metadata (channel / video / comments / subtitles).
📹 YouTube Helper
Podcast Helper
Podcast Helper is a Python library for universal audio stream consumption — URL-in → PCM-out. It accepts local files, direct audio URLs, RSS / Atom feed URLs (auto-picks the latest episode), and any yt-dlp-supported source (YouTube, Vimeo, SoundCloud, Twitch). Built on youtube-helper + ffmpeg + feedparser + podcastparser, with Shannon-correct resampling and either source-native channels or canonical mono downmix.
🎙️ Podcast Helper
🗄️ Storage & transfer
Bucket Helper
Bucket Helper is a Python library for AWS S3 and any S3-compatible object storage — MinIO, Backblaze B2, DigitalOcean Spaces, Cloudflare R2, Wasabi — via boto3. Same shape as SFTP Helper: credentials loader, upload / download / delete / exists / list_prefix, and a remote_tempfile context manager for stage-and-share flows.
🪣 Bucket Helper
SFTP Helper
SFTP Helper is a Python library that provides utility functions for interacting with SFTP servers via Paramiko, with strict host-key verification and a remote_tempfile helper, once you specified your SSH key credentials.
🛜 SFTP Helper
🧩 Standalone tools (not bundled)
Part of the same ecosystem, but they install on their own — the ai-helpers
meta-package does not pull them in.
md2star
md2star is a Markdown → DOCX / PPTX / PDF bridge built on Pandoc, with curated branded templates, Mermaid diagram rendering and bibliography support. A standalone tool (BSD-3-Clause, on PyPI: pip install md2star) — used by notes-helper for document export, but independent of the meta-package.
⭐ md2star
Notes Helper
Notes Helper is a fully-local, privacy-first diarized meeting recorder — audio never leaves your machine; it can export its reports through md2star. It is work in progress and licensed under Apache-2.0; listed here for completeness but not bundled by the ai-helpers meta-package.
🗒️ Notes Helper