---
title: Signal Loom AI
emoji: "🎙️"
colorFrom: purple
colorTo: purple
sdk: gradio
app_file: app.py
pinned: false
---

# 🎙️ Signal Loom AI

**Structured audio understanding for AI systems.**

Don't Transcribe it — Loom it. Loose threads become the lasting fabric in AI Context building.

Upload any audio or video file and get back structured, machine-readable JSON — not raw transcript text. Built for AI systems, RAG pipelines, and developer tools.

Built by **Aster Vale** | Chief of Staff & AI Operations | Signal Loom AI

*Structured audio intelligence — not a transcript, a knowledge object.*
| **60-min file** | ~20-30 min | **~3 minutes** |
| **Privacy** | Cloud | Your machine |
| **Diarization** | ✅ (HF token) | ✅ |
| **Multi-format** | ✅ | ✅ |
| **API access** | ❌ | ✅ |
| **Free tier** | 300 min/mo (demo) | 300 min/mo |

> *"Same engine. Apple Silicon MLX is still the fastest — your Mac processes a 60-min file in ~3 minutes."*

---

## Features

- 🎯 **Whisper MLX** — Fast transcription on Apple Silicon (M1-M3)
- 🔊 **Speaker Diarization** — Know who said what, when *(requires free HF token)*
- 📄 **Multi-format output** — TXT, JSON, SRT, VTT in one pass
- 🤖 **Structured JSON** — Typed output ready for AI pipelines
- 🔒 **Privacy** — Audio processed on dedicated HF GPU infrastructure

## Getting Started

1. Upload an audio or video file
2. Select Whisper model size (base recommended)
3. Enable speaker diarization *(requires free HF token — [get one here](https://huggingface.co/settings/tokens))*
4. Choose output formats
5. Click **Run Transcription**

## Output Formats

| Format | Description |
|--------|-------------|
| **TXT** | Clean transcript text |
| **JSON** | Structured output with speakers, timestamps |
| **SRT** | Subtitle format for video |
| **VTT** | Web caption format |

## For Production

For **unlimited local processing** with your own Mac hardware, no API fees, full API access:

👉 **[signalloomai.com](https://signalloomai.com)** — Free tier: 300 min/month

## About

**Signal Loom AI** — Built for AI consumption, not just human reading.

Powered by OpenAI Whisper, pyannote.audio, and sentence-transformers.

| | |
|---|---|
| **Product** | [signalloomai.com](https://signalloomai.com) |
| **HF Organization** | [signalloom-ai](https://huggingface.co/signalloom-ai) |
| **Support** | support@signalloomai.com |
| **Billing** | billing@signalloomai.com |

---
*Signal Loom AI is operated by Aster Vale — Chief of Staff & AI Operations | AIM Elemental Health Solutions, Inc.*