[{"data":1,"prerenderedAt":116},["ShallowReactive",2],{"seo-verification":3,"blog-heberger-whisper-vps-en":6},{"google":4,"bing":5},"EycwPY2XMyTkVzas3n1ygeNJFGAH513qrMjfDljzsMQ","",{"id":7,"slug":8,"title":9,"excerpt":10,"readTime":11,"views":12,"isPinned":13,"publishedAt":14,"category":15,"categories":21,"featuredImage":23,"bgImage":24,"posterImage":25,"relatedSolution":26,"intro":28,"sections":29,"ctaTitle":72,"ctaBody":73,"ctaButton":74,"ctaUrl":75,"relatedPosts":76},21,"heberger-whisper-vps","How to host Whisper on a VPS","Self-host OpenAI's Whisper on a VPS to transcribe your audio locally: privacy, a private API and controlled cost.",7,377,false,"2026-05-30T00:00:00+00:00",{"id":16,"name":17,"slug":18,"color":19,"icon":20},1,"Artificial Intelligence","intelligence-artificielle","bg-purple-500\u002F10 text-purple-400","ia",[22],{"id":16,"name":17,"slug":18,"color":19,"icon":20},null,"\u002Fblog\u002Fcovers\u002Fbg.svg","\u002Fblog\u002Fcovers\u002Fheberger-whisper-vps-poster.svg",{"categorySlug":20,"appSlug":27},"whisper","Whisper is OpenAI's open-source audio transcription and translation model. Hosted on your VPS, it turns any audio file into timestamped text without sending your recordings to a third-party service. Here is how to deploy it via faster-whisper and expose it as a private API behind a secure reverse proxy.",[30,34,44,47,69],{"type":31,"title":32,"body":33},"h2","Why self-host Whisper on a VPS","Cloud transcription APIs charge per minute of audio and require sending your recordings to external servers — a problem as soon as it involves confidential meetings, HR interviews or medical data. Self-hosting Whisper on a VPS gives you a private transcription endpoint, available 24\u002F7, that processes your files locally. With the `faster-whisper` implementation (based on CTranslate2), you get transcriptions up to 4 times faster than the original implementation, even on CPU. You choose the model size (`tiny` to `large-v3`) according to the speed\u002Faccuracy trade-off you need, and you plug it all into your own applications via a REST API.",{"type":35,"title":36,"items":37},"ul","The concrete benefits of self-hosting",[38,39,40,41,42,43],"Privacy: your sensitive audio never leaves your VPS.","Multilingual transcription and translation into English included in the same model.","Word- or segment-level timestamping, ideal for generating SRT\u002FVTT subtitles.","No duration limit per file, unlike online APIs.","Fixed cost instead of billing per minute of transcribed audio.","Integration via REST API into your internal tools (CRM, podcast, customer support).",{"type":31,"title":45,"body":46},"Hardware and software prerequisites","Whisper is demanding mainly in RAM and compute. On CPU, the `base` or `small` model runs comfortably with 4 GB of RAM and 2 vCPUs; the `large-v3` model rather requires 8 to 10 GB of RAM and 4 vCPUs to stay usable. A GPU VPS (6 GB of VRAM) hugely accelerates `large-v3`. Plan for a few GB of disk for the weights (the `large-v3` weighs ~3 GB) and temporary space for the uploaded audio files. On the software side: Ubuntu 22.04, Docker, `ffmpeg` (essential for decoding audio formats), and a subdomain like `whisper.mydomain.com`.",{"type":48,"title":49,"steps":50},"steps","Step-by-step deployment",[51,54,57,60,63,66],{"title":52,"body":53},"Prepare the environment","Via SSH, install Docker and check for the presence of `ffmpeg` (`apt install ffmpeg`). Create a `whisper\u002F` folder that will contain your `docker-compose.yml` and an `.\u002Faudio` volume for the files to process.",{"title":55,"body":56},"Choose an image with an API","Use an image that directly exposes a REST API, for example `onerahmet\u002Fopenai-whisper-asr-webservice`. In the compose, set `ASR_ENGINE=faster_whisper` and `ASR_MODEL=small` (adjust according to your RAM), and map port `9000`.",{"title":58,"body":59},"Start the service","Start with `docker compose up -d`. On the first call, the container automatically downloads the model weights; mount a volume on `\u002Froot\u002F.cache` so as not to re-download it on every restart.",{"title":61,"body":62},"Test the transcription","Send a file locally: `curl -F \"audio_file=@reunion.mp3\" \"http:\u002F\u002Flocalhost:9000\u002Fasr?output=txt\"`. You should get the transcription back within a few seconds to a few minutes depending on the model.",{"title":64,"body":65},"Expose over HTTPS with authentication","Place Caddy or Nginx in front of port 9000, with authentication (an API key in a header or Basic Auth) to prevent a third party from using your endpoint. Caddy will handle the Let's Encrypt certificate automatically for `whisper.mydomain.com`.",{"title":67,"body":68},"Wire up your workflows","From your applications, call `https:\u002F\u002Fwhisper.mydomain.com\u002Fasr?output=srt` to obtain subtitles directly, or `output=json` for the timestamped segments to reinject into your database.",{"type":70,"body":71},"tip","To process long recordings on CPU without saturating the RAM, enable faster-whisper's VAD (voice activity detection) to skip silences, and set `compute_type=int8`: accuracy barely drops but memory consumption falls sharply, which lets you run `medium` where `large` would not fit. For large volumes, set up a queue (Redis + worker) rather than synchronous calls.","Transcribe privately on a ServOrbit Cloud VPS","Deploy Whisper and its transcription API on a Cloud VPS with Docker and ffmpeg ready to use. Your audio stays with you, your endpoint stays continuously available.","Discover the Cloud VPS","\u002Fvps-cloud",[77,90,103],{"id":16,"slug":78,"title":79,"excerpt":80,"readTime":81,"views":82,"isPinned":13,"publishedAt":83,"category":84,"categories":85,"featuredImage":23,"bgImage":24,"posterImage":87,"relatedSolution":88},"heberger-open-webui","How to Host Open WebUI on a VPS","A complete guide to deploying Open WebUI on your own VPS. Keep control of your data, avoid cloud API costs, and access your LLMs from a clean web interface.",6,3200,"2026-06-01T00:00:00+00:00",{"id":16,"name":17,"slug":18,"color":19,"icon":20},[86],{"id":16,"name":17,"slug":18,"color":19,"icon":20},"\u002Fblog\u002Fcovers\u002Fheberger-open-webui-poster.svg",{"categorySlug":20,"appSlug":89},"open-webui",{"id":91,"slug":92,"title":93,"excerpt":94,"readTime":11,"views":95,"isPinned":13,"publishedAt":96,"category":97,"categories":98,"featuredImage":23,"bgImage":24,"posterImage":100,"relatedSolution":101},2,"deployer-dify-vps","Deploying Dify on a VPS: AI Workflows Under Control","Install Dify on a ServOrbit VPS to build agents, chatflows and AI apps without losing control of your data.",2480,"2026-02-11T00:00:00+00:00",{"id":16,"name":17,"slug":18,"color":19,"icon":20},[99],{"id":16,"name":17,"slug":18,"color":19,"icon":20},"\u002Fblog\u002Fcovers\u002Fdeployer-dify-vps-poster.svg",{"categorySlug":20,"appSlug":102},"dify",{"id":81,"slug":104,"title":105,"excerpt":106,"readTime":107,"views":108,"isPinned":13,"publishedAt":109,"category":110,"categories":111,"featuredImage":23,"bgImage":24,"posterImage":113,"relatedSolution":114},"openclaw-vps","Deploying OpenClaw on a VPS","A guide to deploying OpenClaw on your own VPS. Keep control of your AI agents and your data within your own infrastructure.",5,422,"2026-06-11T00:00:00+00:00",{"id":16,"name":17,"slug":18,"color":19,"icon":20},[112],{"id":16,"name":17,"slug":18,"color":19,"icon":20},"\u002Fblog\u002Fcovers\u002Fopenclaw-vps-poster.svg",{"categorySlug":20,"appSlug":115},"openclaw",1785628448603]