Skip to main content

SubsAI

SubsAI is available in the NetActuate Marketplace as a one-click, open-source appliance you can deploy into any NetActuate PoP. Generate subtitles and captions from audio or video with Whisper, in a web UI. It is grouped under the Media & Streaming category.

What It Does​

SubsAI is an open-source subtitle and caption generator built on OpenAI Whisper and faster-whisper, wrapped in a friendly Streamlit web UI. Upload an audio or video file, pick a Whisper model, transcribe (and optionally translate) to subtitles, review and edit the result, then export standard subtitle formats such as SRT and VTT.

Key features

  • Automatic speech-to-text captioning powered by OpenAI Whisper and faster-whisper
  • Multiple model sizes and languages, with translation support
  • Open Streamlit web UI: upload media, transcribe, edit, and export in the browser
  • Standard subtitle export (SRT, VTT, and more) ready for players and editors
  • Fully self-hosted and offline: your media never leaves your server
  • CPU inference by default, with a media volume for uploads and a persisted models cache

Use cases

  • Caption podcasts, webinars, lectures, and video-on-demand libraries
  • Generate first-pass transcripts and subtitles for human review
  • Localize content by transcribing and translating audio tracks

Why run it on the NetActuate edge Running SubsAI in a PoP near your media keeps large uploads and captioning workloads on infrastructure you control, avoids per-minute cloud transcription fees, and keeps sensitive audio and video private to your own instance.

Deployed from the NetActuate marketplace, SubsAI boots ready to use: the Streamlit web UI answers on HTTP port 8501 with no login to configure. Whisper models are downloaded on first use and cached to a persistent volume, so the first transcription warms the model and later runs reuse it.

Vendor and Project​

SubsAI is an open-source project, offered here under the Open Source listing with best-effort community support.

NetActuate supports the underlying infrastructure. Application-level support follows the listing SLA class (open-source, best effort).

Sizing​

vCPURAMDisk
Minimum24 GB40 GB
Recommended48 GB80 GB

No VPU (hardware acceleration) is required for this appliance. Choose a size at deploy based on your expected load.

Configuration Fields​

When you deploy, you provide these fields. They are written into the appliance at first boot.

FieldRequiredDefaultNotes
Web UI portNo8501Host port the Streamlit web UI is published on (default 8501). The container always listens on 8501; this only changes the host port.

Using the Appliance​

Start captioning in minutes

  1. Open the web UI. Browse to http://YOUR_VM_IP:8501/ . The Streamlit UI has no login, so it is ready as soon as the instance is up.
  2. Transcribe. Upload an audio or video file, choose a Whisper model and language, and run the transcription. The first run downloads the chosen model (cached for later runs).
  3. Edit and export. Review and edit the generated subtitles, then export SRT, VTT, or another supported format.

Exposure posture: the appliance serves plain HTTP on port 8501 with no authentication. Put a TLS-terminating proxy and access control in front before exposing it on an untrusted network.

FAQ​

Is there a software license fee? No. SubsAI is open source and free to run. You pay only for the NetActuate infrastructure and bandwidth.

Which port does the appliance serve on? The primary service is published on port 8501 by default; see the configuration fields for any adjustable ports.

Who supports it? NetActuate operates the underlying infrastructure. The application itself is community-supported open source (best-effort SLA class).

Version and Changelog​

VersionStatusReleased
main-20260713Current (default)2026-07-13

Deploy​

Need Help?​

Contact support@netactuate.com or open a support ticket from the portal.