Verity Mod Groq API Key Setup

What the Groq credential does

Verity JE can use Groq to send a prompt to a cloud language model and receive a response. The credential identifies and authorizes those requests under your Groq account. It is not a Verity download code, a Minecraft login, or a value that this website should ever receive.

Treat it like a password. Anyone who obtains it may be able to make requests under your account until it is revoked or limited. The safe flow is simple: create it in GroqCloud, place it only in the current trusted Verity JE configuration on your computer, and keep it out of screenshots, logs, chat, streams, and repositories.

Before creating a credential

Finish the non-AI part of the Java setup first. Minecraft should launch with the exact loader and game version. Verity JE and its current dependencies should load in a clean profile. The companion or documented interaction should appear in a new test world.

If Minecraft crashes before the title screen, a Groq credential will not fix it. Resolve Java runtime, loader, dependency, duplicate-file, or mod-conflict errors before adding a cloud provider. This separation also reduces the amount of configuration you need to expose while asking for help.

Use the current checked Java route, Forge 1.20.1, when possible. The maintainer lists the NeoForge 1.21.1 branch as deprecated and buggy, so a provider error on that branch may be mixed with a branch-specific mod problem.

Create the credential in GroqCloud

Open the official GroqCloud Console from the Sources section of this page. Sign in to your own account and open the API Keys area. Create a new credential specifically for this Verity test so that you can identify and revoke it without affecting an unrelated project.

Give it a local label that describes the use, such as “Verity test profile.” Do not include the secret itself in the label. When Groq displays the value, copy it directly into a temporary secure workflow and move immediately to the local Verity configuration. Secret values may only be shown once.

Do not create a credential through a “free key generator,” paste site, support bot, video description mirror, or form claiming to configure Verity remotely. The credential originates in GroqCloud. Verity Mod Guide has no setup form and cannot validate it for you.

Enter it only in the current Verity flow

Use the configuration location shown by the current Verity JE project instructions or its maintainer-linked setup tutorial. The mod interface or configuration shape can change between releases, so this guide does not invent a permanent filename or field when the maintainer is the source of truth.

Paste the credential once and check for leading or trailing spaces. Do not wrap it in extra quotation marks unless the current configuration explicitly requires them. Do not paste the value into Minecraft chat; chat can be logged, shown to other players, or captured by a stream.

If the setup stores a local configuration file, protect that file as a secret. Do not include it when sharing the whole profile, uploading logs, making a modpack archive, or committing launcher files to Git. A .gitignore entry is useful for repositories, but it does not erase a secret already committed to history.

First test

Restart the game if the maintainer setup requires it. Open a new test world and use a short text prompt in English. Text isolates the language-model connection from microphone permissions, speech recognition, and voice output. Wait for one request to finish before sending another.

There are three useful outcomes:

1. Text response arrives. The cloud model path works. You can test voice separately.
2. Authentication is rejected. Re-check the credential value, whether it was revoked, and whether it was entered in the correct local field.
3. Timeout or service error. Check network access, service availability, account limits, and the exact error without exposing the secret.

Record the error code or message, not the credential. When a support helper asks to “see the key,” decline. Legitimate troubleshooting can verify that a value exists and is accepted without publishing it.

Common setup failures

Hidden whitespace: copying from a formatted document or mobile note can add spaces or line breaks. Copy directly from GroqCloud and paste into the intended local field.

Wrong profile: you may edit one launcher instance while starting another. Confirm that the configuration belongs to the profile containing the checked Verity release.

Old tutorial location: a video may show an earlier UI or config path. Compare it with the current project description and changelog.

Revoked or replaced value: if you rotated the credential, make sure the local configuration contains the new value and the old process was restarted.

Network filtering: a firewall, school network, corporate policy, VPN, or DNS filter can block the request. Test with an allowed network and follow its rules; do not disable managed security controls without authorization.

Usage or service limit: read the response and GroqCloud account information. Rapid repeated requests can make diagnosis harder and may consume more usage.

Add voice only after text works

The Verity JE project describes text AI across languages, while speech-to-text and text-to-speech were tested in English. A working Groq text response proves only the model request path. Microphone access, input device selection, speech recognition, and audio output remain separate.

Test one audio direction at a time. First verify that microphone input produces recognized text. Then verify that a known text response can be spoken. Use simple English during diagnosis. Do not replace a working credential merely because the microphone is denied by the operating system.

If the credential leaks

Revoke it in GroqCloud immediately. Rotation is the primary containment action; editing the screenshot or deleting a message may not remove copies. Create a replacement, update only the trusted local configuration, restart the affected process, and verify that the old value no longer works.

Search likely exposure locations: chat history, support posts, screenshots, stream recordings, shell history, shared profile archives, cloud-sync folders, and Git history. Remove or restrict those artifacts where possible, but still assume the old value was copied.

Ongoing hygiene

Use a separate credential for Verity so it can be revoked independently. Remove credentials you no longer use. Review Groq account usage for unexpected activity. Keep prompts free of passwords, private documents, personal addresses, and information you would not send to a cloud service.

When sharing a troubleshooting log, make a copy, redact secrets completely, and inspect the final text before uploading. Do not rely on partial masking or a promise that a private message will stay private.

If you prefer not to send prompts to a cloud model, use the local Ollama setup. Ollama avoids a Groq credential but requires a running local model service and enough computer resources. It is an alternative trust boundary, not a one-click mode.