Speech-to-Text
Speech-to-Text osFoundry community catalog में एक app है। Self-hosted speech-to-text service running OpenAI's Whisper models — accurate transcription in 90+ languages, speaker diarization (optional), VAD-trimmed faster inference, multiple model sizes (tiny → large-v3), REST API + browser upload UI. Powered by the Whisper ASR Webservice (ahmetoner/whisper-asr-webservice). CPU is workable for medium models; GPU is needed for large + real-time.
विवरण
- Workspace: osfoundry
- Category: COMMUNICATION
- मूल्य: Free
- Access: Community
Features
- Speaker diarization (optional)
- VAD-trimmed faster inference
- Multiple model sizes (tiny → large-v3)
- REST API + browser upload UI
Documentation
Documentation को upstream project द्वारा अंग्रेज़ी में मेंटेन किया जाता है।
# Speech-to-Text
Self-hosted Whisper transcription, powered by the Whisper ASR Webservice.
## Performance
- **tiny / base** — usable on CPU (real-time-ish)
- **small / medium** — CPU works for batch transcription; GPU for real-time
- **large-v3 / distil-large-v3** — GPU strongly recommended
## Features
- 90+ languages
- Speaker diarization (optional, via pyannote.audio)
- VAD (voice activity detection) to skip silence + speed up batch jobs
- Output formats: JSON, text, SRT, VTT, TSV
- REST API: POST audio file → returns transcript
- Browser upload UI at `/`
## Packaging
Thin wrapper around the official `onerahmet/openai-whisper-asr-webservice` image (CPU variant). Downloaded models cached at `/root/.cache`.
osFoundry में Speech-to-Text का उपयोग कैसे करें
एक क्लिक में Speech-to-Text को अपने workspace में install करें, फिर अपने stack के लिए prompts, tools, या configuration को customise करने के लिए इसे osStudio में fork करें। आपके workspace का कोई भी सदस्य वहीं से आगे बढ़ा सकता है जहाँ आपने छोड़ा था।
Community से अन्य apps
- CRM — Contacts, deals, और pipeline tracking के साथ customer relationship management।
- Kanban Board — एक Trello-style kanban and project board के साथ cards, boards, calendar and table views, and per-board properties. Powered by Focalboard (standalone personal server). Embedded SQLite एक persistent volume पर.
- Helpdesk — SLA tracking के साथ ticket triage और customer support inbox।
- Page Builder — Visual drag-and-drop page builder के साथ sections, themes, SEO, and publishing
- Website Builder — Multi-page website builder के साथ CMS collections, global navigation, footer, themes, and publishing
- Storefront — Product catalog, cart, और checkout के साथ e-commerce storefront।