Book a demo
Book a demo
Login

faster-whisper Hosting Live In 5 Minutes

Deploy faster-whisper hosting and run speech-to-text for Home Assistant voice assistants on your own server. xCloud runs the pinned faster-whisper v3.8.1-ls9 image, mounts a persistent volume for the speech model and publishes the Wyoming port, so audio is transcribed by Whisper models on your CPU instead of a cloud transcription service. There is no web page or login, so you restrict the port to your own clients straight after install.

Deploy your faster-whisper
  • No terminal
  • No technical skills needed
  • No lock-in, cancel anytime

What is faster-whisper?

faster-whisper is a reimplementation of OpenAI's Whisper speech recognition model using CTranslate2, a fast inference engine for Transformer models. Its maintainers describe it as up to 4 times faster than openai/whisper for the same accuracy while using less memory, and 8-bit quantization improves efficiency further on both CPU and GPU.

The LinuxServer.io container this template deploys wraps it in a Wyoming protocol server. Wyoming is the protocol Home Assistant Assist uses to reach speech services, so you add the Wyoming integration, enter the server's address and port, and transcription runs on your own server.

From Sign-Up to a Running Wyoming Server In 3 Easy Steps

A local speech-to-text server normally means choosing an image, a model, a volume and a published port before Home Assistant can talk to it. This is the same result without assembling any of it.

  1. Step 01

    Sign Up

    Create your xCloud account and pick faster-whisper from the OneClick catalog. Choose your target server — there are no extra fields to fill in, and no credentials are generated because the server has none.

  2. Step 02

    We Deploy It For You

    One click. We bring up the single faster-whisper container, pinned by immutable digest, mount the faster_whisper_config volume for the Hugging Face model cache, and publish the Wyoming port (10300/tcp inside the container) on its own host port. The first start downloads the speech model from huggingface.co, so allow 2 to 5 minutes.

  3. Step 03

    Connect Home Assistant

    Note the Server Address and Port in the installation credentials. In Home Assistant, add the Wyoming Protocol integration and enter that address and port, then restrict the port to your Home Assistant host's IP in your cloud provider's firewall.

Everything faster-whisper Does, On Your Own Server

faster-whisper runs here as a Wyoming speech-to-text server: Whisper models on your CPU, a model that survives restarts, and settings you control through environment variables.

  • Wyoming Speech-to-Text

    Serves transcription over the Wyoming protocol, so Home Assistant's Wyoming integration and any other Wyoming client can connect at the server address and port.

  • Whisper Models On Your CPU

    faster-whisper reimplements OpenAI's Whisper with CTranslate2. The default model, base-int8 on amd64, runs on CPU and needs about 1 GB of RAM as a baseline.

  • Model, Language And Beam Size

    Set WHISPER_MODEL (for example small-int8), WHISPER_LANG and WHISPER_BEAM in the environment file and redeploy; the values are read when the container starts.

  • Models Kept On A Volume

    Downloaded models and the Hugging Face cache live on the faster_whisper_config volume, so an xCloud Restart does not download them again.

  • No Accounts Or API Keys

    There is nothing to sign up for and no key to rotate. That also means no authentication: access is controlled by your firewall.

  • Pinned By Digest

    The LinuxServer.io image is pinned by immutable digest, so a redeploy does not silently change the version that is running.

Everything You Need To Run Your Speech-to-Text 24/7

Managed hosting for faster-whisper, so the parts that keep it online are not your problem.

  • faster-whisper v3.8.1-ls9 deployed instantly
  • LinuxServer.io image pinned by digest
  • Speech model kept on a persistent volume
  • No credentials or API keys to manage
  • Server backups and snapshots
  • Server security updates included
  • 30+ server locations
  • Unused balance refunded

What You Can Do With faster-whisper

  • Local voice control for Home Assistant

    Point Home Assistant's Wyoming Protocol integration at the server so spoken commands are transcribed on your own hardware.

  • One shared speech server for several clients

    Any Wyoming client can connect to the same address and port, so more than one assistant or device can share one transcription server.

  • Transcription without a per-minute cloud service

    Whisper models run on the CPU of a server you control, with no account or API key to manage.

  • Trying a different model or language

    Change WHISPER_MODEL, WHISPER_LANG or WHISPER_BEAM in the environment file, redeploy, and the new settings apply on the next start.

faster-whisper vs Alternatives

OpenAI Whisper (openai/whisper)
The original Whisper implementation. faster-whisper's maintainers report it as up to 4 times faster than openai/whisper for the same accuracy while using less memory.
whisper.cpp
A C/C++ port of Whisper. In faster-whisper's own small-model CPU benchmark (8 threads, beam size 5), whisper.cpp fp32 used 1049 MB of RAM against 1477 MB for faster-whisper int8, while faster-whisper int8 took 1m42s against 2m05s.
Home Assistant Whisper add-on
The Home Assistant add-on that also serves faster-whisper over Wyoming. It is installed through the Supervisor on the Home Assistant machine; this page runs the same kind of Wyoming server on a separate server instead.
Home Assistant on xCloud
A different job: Home Assistant itself, cloud-hosted. It can be the client that talks to this speech server.

Simple Pricing. Everything Included.

Dedicated Cloud VPS sizes, pre-configured for faster-whisper hosting. Pick the one that fits, and resize any time.

Cloud VPS 6 GB

Most popular

A speech-to-text server for one Home Assistant setup.

$24.99per month

  • 6 GB RAM
  • 4 vCPU cores
  • 100 GB NVMe SSD
  • 30 TB
  • Unlimited
Get started

Cloud VPS 16 GB

More headroom for a larger Whisper model or other services on the same server.

$59.99per month

  • 16 GB RAM
  • 6 vCPU cores
  • 200 GB NVMe SSD
  • 30 TB
  • Unlimited
Get started

Every size is a dedicated Cloud VPS we provision, patch, monitor and restore. Billed monthly with no lock-in — delete the server and the unused balance comes back to your account. The LinuxServer.io faster-whisper image repository is licensed under GPL-3.0.

Docker hosting

Already Have a Server? Bring Your Own

Connect any VPS — DigitalOcean, Vultr, Linode, AWS, Hetzner or bare metal — and deploy faster-whisper on it through the same panel, for a per-server management fee instead of a Cloud VPS rental.

Free

Start your journey without cost.

$0forever

  • 1 server
  • 10 sites
Start free

Starter

Most popular

Your rate with 2–5 servers connected.

$5per server / month

  • 2–5 servers
  • Unlimited sites
  • All features included
  • Bring any VPS provider
Get started

Professional

The same platform, discounted at 6–10 servers.

$4per server / month

  • 6–10 servers
  • Unlimited sites
  • All features included
  • Bring any VPS provider
Get started

Agency

The same platform, discounted at 11+ servers.

$3per server / month

  • 11+ servers
  • Unlimited sites
  • All features included
  • Bring any VPS provider
Get started

Priced per connected server, so your rate adjusts automatically as you add or remove servers. You pay your own provider for the server itself.

Self-managed hosting

Ready To Run Your Own Speech-to-Text Server?

faster-whisper on xCloud runs on a dedicated Cloud VPS that we provision, patch, monitor and restore. Deploy faster. Own the server. Stay in control.

Hear what people are saying about us

See why agencies, developers, startups, and growing businesses choose xCloud to power their projects.

xCloud works really well, I am surprised by its performance being this the release version, I have tried many paid platforms such as runcloud, cloudpages or serveravatar, as well as free platforms such as CyberPanel, CloudPanel or Hestia Control Panel and direct competitors such as SpinupWP and FlyWP. Of all those that I have tried, the platform that works best for WordPress is SpinupWP and I believe that xCloud can reach and surpass that development, its roadmap is promising. Congratulations to the xCloud team, I hope they become the leading platform in the segment, it has all the potential to achieve it!
Brian Geovanny
I've been with runcloud for the last 3 years. However, after trying xcloud for the last month, I'm switching over. They are on a roll with their setup.
Kevin Pineda
I'm moving my servers to xCloud, a cloud control panel by M Asif Rahman and the WPDeveloper team. Their roadmap looks interesting and no, there are no team mates nor API limits with xCloud! #xCloud #wordpress #hosting
Leo Koo
How Cloud Nine Web Elevated Client Experience While Streamlining Hosting Operations using xCloud
Ed Ellingham
xCloud is like having an expert server team on call — without the big agency costs. It's given me back my time and given my clients peace of mind. Highly recommended for freelancers and small teams who want reliable performance and security.
Dumitru Butucel
xCloud isn't just a solution. It's like one of that friend who got your back when you screw things up pretty bad.
Waqar Ahmed
Trust me when I say, once people explore the potential of xCloud they gonna switch from other panels, just keep delivering the best tech, lots of love for the team 😍😍
Rahul Singh
So far my experience has been smooth like silk. I didn't imagine that configuring and managing a VPS would be so easy. As of today, I have deployed 8 sites. The support is good, and they treat users with respect, even if they ask stupid questions (myself included). For the future, I hope for greater flexibility in scheduled backups and more comprehensive and consistent documentation. I'm sure that within a few months, xCloud will become the leader in its segment. This community is amazing, and the Staff here is super helpful.
Massimo Villa
Came from cloudways then to runcloud then to xcloud. Looks like I'm staying here.
Gerson El
I've recently taken all of my Vultr-hosted sites and gotten rid of cPanel for them to substitute it with xCloud. I have to say, I'm really impressed with xCloud so far! The interface is definitely the standout feature for me.
Tony Lewis
I came from Cloudways and won't go back. Highly impressed with xCloud. Glad I gave them a chance.
Jared McDowell
I like xCloud better than RunCloud, but one thing I'll point out is that some years ago RunCloud was hungry for business, the support was outstanding, and the community was active and helped each other. Maybe it was sold, there was a change in management, or they stopped being hungry, but the quality of the RunCloud offering declined and it hasn't been moving forward quickly. My point is that currently the xCloud team has the edge and it is theirs to keep or lose
David McCan
How Kevin Heinrichs Cut Hosting Costs by 84% While Running WooCommerce & Node.js Sites Efficiently
Kevin Heinrichs
I had 150 sites on cloudways and am in the process of moving them to xcloud. Much faster and better priced.
Dan Spinoza
Dear xCloud Team, I have been using xCloud for some time now and am genuinely impressed with its capabilities and the flexibility it offers by allowing users to bring their own VPS for management. It's a fantastic service, and my experience so far has been very positive. Successful migrated 5 sites on a single server. Xcloud migration tool worked great. There were few hiccups with security plugin like MalCare but disabling the plugin prior to migration worked just fine.
Rahil Maknojia
Came from runcloud. Tried xcloud and never came back.
Karl Fanega
How Advanced Web Strategies Saved Over $2,000 & Recovered 56 Hours per Month Managing 70+ Client Websites
Gary Moody
xCloud gave me what no other hosting platform could: the flexibility of a VPS with the convenience of managed WordPress. As a solo founder running an entire business on one server, that combination is an important unfair advantage.
Jorge de los Reyes Martínez
I use Server Avatar and xCloud and I'll sooner use xCloud than Server Avatar personally.
Jay Pagano
How Newman Web Solutions Ensured Perfect Uptime and Seamless Scaling For 120+ WordPress Sites with xCloud
Lori Newman
I too have moved over to xCloud. It's pretty sweet. One click n8n and uptime Kuma apps
John Aperture
I went from Cloudways to xCloud. No intention on switching in the foreseeable future.
Blaine Moore

Frequently Asked Questions

Feel free to contact us with any questions or concerns you may have.

How do I connect Home Assistant?

Add the Wyoming Protocol integration in Home Assistant and enter the Server Address and Port shown in the installation credentials.

Is there a web page or login?

No. It is a raw Wyoming TCP service with no web page and no login, so there is no domain and no HTTPS.

Is it safe to leave the port open?

No. The port is open to the internet after install and the server has no authentication, so anyone who finds it can send audio and use up the server's CPU. Restrict it to your Home Assistant host's IP in your cloud provider's firewall or security group. Docker publishes the port past the server's own ufw rules, so a ufw rule alone will not close it.

Firewall management in xCloud

Is the audio encrypted?

No. Audio is sent unencrypted over the Wyoming connection, so prefer a private network or VPN between the client and this server and avoid untrusted networks.

How long does the first start take?

Allow 2 to 5 minutes. The first start downloads the speech model from huggingface.co and loads it before the port opens, so the server needs outbound internet access.

Can I use a larger model?

Yes. Set WHISPER_MODEL (for example small-int8) in the environment file and redeploy. A larger model needs more memory and CPU, and a new model is downloaded on the next start.

Edit environment variables and redeploy

Does it use a GPU?

No. This template runs on CPU only.

Why did my model stop downloading?

Setting LOCAL_ONLY to any value, including false, stops model downloads. Leave that line commented unless the model is already on the volume.

What should I back up?

The faster_whisper_config volume, which holds the downloaded speech models and the Hugging Face cache. The models can be downloaded again if you lose it.

Backups in xCloud

What survives a restart?

The downloaded model on the persistent faster_whisper_config volume, so an xCloud Restart does not download it again.

Does xCloud automatically back up or update faster-whisper?

No. The template pins faster-whisper v3.8.1-ls9 by immutable digest, so existing sites are not automatically upgraded. Read the upstream release notes, then bump the readable tag and digest together on your own schedule. Server-level backups and snapshots are available on every Cloud VPS.

What are the server requirements, and why does this page sell 6 GB?

The template's baseline asks for 2 CPU cores, 1024 MB of RAM and 5 GB of disk; measured idle use in QA was about 408 MiB with the default model. This page sells the 6 GB tier as the entry rung, with real headroom above that baseline and room to try a larger model.

Is xCloud officially partnered with faster-whisper?

No. No official partnership or endorsement between xCloud and the faster-whisper, LinuxServer.io or Home Assistant projects has been verified. This is a deployment and server-management option for open-source software.

Can I cancel anytime?

Yes. There is no lock-in — cancel any time. Hosting is billed monthly and charged for what you actually use, so when you delete the server the unused balance is refunded to your account, less up to 10% in payment-processing fees.

Related apps

Other apps people run next to faster-whisper on the same server.

Related resources

The firewall, backup and environment guides that matter most once faster-whisper is live.

More AI apps in one click

Browse all one-click apps →

Ready to Run Your Own Speech-to-Text Server?

Connect your first server in minutes. No credit card required, and no plan you have to grow into.

Deploy faster-whisper now