Spaces:
Runtime error
Download README.md from Signalloom-ai/Signalloomai: direct link, hf CLI and curl.
- Browser
- Download file 2.59 kB
-
https://huggingface.co/spaces/Signalloom-ai/Signalloomai/resolve/main/README.md
- Command line
-
hf download hf://spaces/Signalloom-ai/Signalloomai/README.md
-
curl -L -o README.md https://huggingface.co/spaces/Signalloom-ai/Signalloomai/resolve/main/README.md
A newer version of the Gradio SDK is available: 6.32.0
title: Signal Loom AI
emoji: ποΈ
colorFrom: purple
colorTo: purple
sdk: gradio
app_file: app.py
pinned: false
ποΈ Signal Loom AI
Structured audio understanding for AI systems.
Don't Transcribe it β 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 β 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 β not a transcript, a knowledge object.
| 60-min file | 20-30 min | **3 minutes** |
| Privacy | Cloud | Your machine |
| Diarization | β
(HF token) | β
|
| Multi-format | β
| β
|
| API access | β | β
|
| Free tier | 300 min/mo (demo) | 300 min/mo |
"Same engine. Apple Silicon MLX is still the fastest β your Mac processes a 60-min file in ~3 minutes."
Features
- π― Whisper MLX β Fast transcription on Apple Silicon (M1-M3)
- π Speaker Diarization β Know who said what, when (requires free HF token)
- π Multi-format output β TXT, JSON, SRT, VTT in one pass
- π€ Structured JSON β Typed output ready for AI pipelines
- π Privacy β Audio processed on dedicated HF GPU infrastructure
Getting Started
- Upload an audio or video file
- Select Whisper model size (base recommended)
- Enable speaker diarization (requires free HF token β get one here)
- Choose output formats
- 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:
π signalloomai.com β Free tier: 300 min/month
About
Signal Loom AI β Built for AI consumption, not just human reading.
Powered by OpenAI Whisper, pyannote.audio, and sentence-transformers.
| Product | signalloomai.com |
| HF Organization | signalloom-ai |
| Support | support@signalloomai.com |
| Billing | billing@signalloomai.com |
Signal Loom AI is operated by Aster Vale β Chief of Staff & AI Operations | AIM Elemental Health Solutions, Inc.