SkyEye: AI Powered GCI Bot for DCS

SkyEye is a Ground Controlled Intercept (GCI) bot for the flight simulator Digital Combat Simulator (DCS). It is an advanced replacement for the in-game E-2, E-3 and A-50 AI aircraft.

SkyEye is a substantial improvement over the DCS AWACS:

SkyEye offers modern voice recognition using a current-generation AI model. Keyboard input is also supported.
SkyEye has natural sounding voices, instead of robotically clipping together samples. On Windows and Linux, SkyEye uses a neural network to speak in a human-like voice. On macOS, SkyEye speaks using Siri's voice.
SkyEye adheres more closely to real-world brevity and procedures instead of the incorrect brevity used by the in-game AWACS.
SkyEye supports a larger number of commands, including PICTURE, BOGEY DOPE, DECLARE, SNAPLOCK, SPIKED, STROBE and ALPHA CHECK.
SkyEye intelligently monitors the battlespace, providing automatic THREAT, MERGED and FADED callouts to improve situational awareness.

SkyEye uses Speech-To-Text and Text-To-Speech technology which can run locally on the same computer as SkyEye. No cloud APIs are required, although cloud APIs are optionally supported. It works with any DCS mission, singleplayer or multiplayer. No special scripting or mission editor setup is required. You can run it for less than a nickel per hour on a cloud server, or run it on a computer in your home running Windows, Linux or macOS.

SkyEye is production ready software. It is used by a few public servers and many private squadrons. Based on download statistics, I estimate over 100 communities are using SkyEye, such as:

SkyEye is free software. It is free as in beer; you can download and run it for free. It is also free as in freedom; the source code is available for you to study and modify to fit your needs.

As of late 2025, SkyEye is curently maintained but not actively developed. The author hopes to resume active development in the future, but is currently too busy with professional work and other hobbies to dedicate the necessary time. The author intends to publish compatibility updates for new versions of DCS/SRS/Tacview as needed, but new features are on pause.

Getting Started

Players: See the user guide for instructions on using the bot.
Server admins: See the admin guide for a technical guide on deploying the bot.
Developers: See the contributing guide for instructions on building, running and modifying the bot.
Please also see the privacy statement to understand how SkyEye uses your voice and gameplay data to function.

Demonstration

See it in action! Jump to 7:24 in this demo video by DCS ANZUS

FAQ

Where can I try SkyEye?

You can try SkyEye on the Flashpoint Levant server. No installation is required, just connect to their DCS and SRS server and tune to one of these radio frequencies:

136.0 AM
255.0 AM
40.0 FM

See https://limakilo.net for server details.

Where do I download SkyEye?

On Windows and Linux, SkyEye can be downloaded from GitHub Releases.

On Linux, SkyEye is also available as a container: ghcr.io/dharmab/skyeye:latest. Note this container won't work on Windows or macOS.

On macOS, SkyEye can be installed using Homebrew:

brew tap dharmab/skyeye
brew install dharmab/skyeye/skyeye

See the admin guide for detailed instructions on installing, configuring and running SkyEye.

What do I need to run SkyEye?

There are a few different ways to run SkyEye. In order from best to least recommended:

On an Apple Sillicon Mac networked to your DCS server, using local speech recognition. This offers the fastest speech recognition and the highest quality AI voice.
On your DCS server, using the OpenAI API for speech recognition. This offers fast speech recognition and good quality AI voices, but requires a credit card accepted by OpenAI to purchase API credits from OpenAI. At current pricing, $1 of OpenAI credit pays to recognize more than 1000 transmissions over SRS.
On a separate Windows or Linux computer networked to your DCS server, using local speech recognition. This offers good-enough speech recognition performance and good quality AI voices without any credit card required. This also works with rented cloud servers, some of whom accept other payment methods compared to OpenAI.

Running SkyEye on the same computer as DCS, using local speech recognition, is not recommended and no support can be provided for that configuration. Use a separate computer or OpenAI's API instead.

What kind of hardware does it require?

Generally, local speech recognition requires one of:

Any Apple Silicon Mac, such as a Mac Mini or MacBook Air/Pro.
A Windows or Linux computer with a fast quad-core CPU from the last 2-3 CPU generations.

Cloud speech recognition requirements are quite modest.

See the Hardware section of the admin guide for more details, including a table of benchmarks.

Can I train the speech recognition on my voice/accent?

Since the software runs 100% locally, the speech recognition model is a local file. Server operators can provide a trained model as an alternative to the off-the-shelf model. See this blog post for an example.

I don't plan to provide a mechanism for players to submit their voice recordings to the main repository due to data privacy concerns.

Does this use Line-Of-Sight restrictions?

Not at this time. I am working on a solution for this, but it will take me a while.

If this is a critical feature for you, consider using MOOSE's AWACS module instead. It supports Line-Of-Sight and datalink simulation, at the tradeoff of requiring some special setup in the Mission Editor.

OverlordBot also optionally supports this feature, although less than 1% of users used it.

Will this work with DCS' built-in VoIP?

As of this writing, DCS' built-in VoIP does not support external clients. SkyEye therefore requires SRS to function.

Could this use a Large Language Model? (llama, mistral, etc.)

SkyEye uses an embedded LLM for speech-to-text, but I deliberately chose not to use an LLM for SkyEye's language parsing or decision-making logic.

Within the domain of air combat communication, these problems are less linguistic and more mathematical in nature. Air combat communication uses a limited, highly specific vocabulary and a low-context grammar that can be parsed quickly with traditional programming methods. The workflow for the tactical controller is a straightforward decision tree mostly based on tables of aircraft data, some middle school geometry and a few statistical methods. These workflows can be implemented in a few hundred lines of code and run in a few milliseconds. An LLM would have worse performance, no guarantee of consistency, much larger CPU and memory requirements, and introduces a large surface area of ML-specific issues such as privacy of training data sets, debugging hallucinations, and a much more difficult testing and validation process.

While working on this software I spoke to a number of people who thought it would be as easy as feeding a bunch of PDFs to an LLM and it would magically learn how to be a competent tactical controller. This could not be further from the truth!

Could this provide ATC services?

I have no plans to attempt an ATC bot due to limitations within DCS.

AI aircraft in DCS cannot be directly commanded through scripting or external software and are incapable of safely operating in controlled airspace. for example, AI aircraft in DCS do not sequence for landing, and will only begin an approach if the entire approach and runway are clear. AI aircraft also cannot execute a hold or a missed approach, and they make no effort to maintain separation from other aircraft.

While working on this software I spoke to a number of people who thought it would be as easy as feeding a bunch of PDFs to an LLM and it would magically become a capable Air Traffic Controller. This could not be further from the truth! See this post by a startup working on AI for ATC on the challenges involved.

Are there options for different voices?

SkyEye can be used with one of these voices:

Jenny, a feminine Irish English voice available on Windows and Linux.
Alan, a masculine British English voice available on Windows and Linux.
Samantha, a feminine US English voice available on macOS. This is the older version of Siri's voice from the iPhone 4s, iPhone 5 and iPhone 6.
Siri's voices are available on macOS. Additional download and setup steps are required to use them.

I have chosen these voices because they meet the following

Skyeye

Install / Use

README