$ loading_
Automate LLM inference, audio translation, and TTS workflows with GroqCloud APIs.
The material indicates an open-source skill, but its actual functionality depends on Composio MCP and GroqCloud remote services. No clear high-risk red flags are evident, but it does involve account linking, remote data transfer, and sending prompts or audio to external services, so caution is appropriate.
The material says no local environment variables are needed, but it explicitly requires connecting a GroqCloud account through Composio MCP and completing authentication, which implies third-party account authorization/token use. No unusually privileged credential request is shown, but the auth flow passes through Composio and rube.app, so users should review token custody and revocation.
This skill depends on the remote MCP endpoint `https://rube.app/mcp` and uses Composio to reach GroqCloud APIs; chat messages, model queries, and audio translation inputs may all be sent to external services. The egress appears aligned with the stated purpose, with no obvious unrelated exfiltration, but user content is not processed purely locally.
Per the objective checks, this is prompt-only, and the material does not describe local shell execution, software installation, or use of privileged system capabilities. The evidence points to invoking existing MCP tools for remote API calls rather than executing arbitrary local code.
The audio translation feature accepts `file_path` as a local path, HTTP(S) URL, or base64 data URL, indicating it can read user-specified audio sources and send the contents for remote processing. There is no stated broad filesystem traversal, but access to specified files and outbound transfer still requires user care over input scope.
The source is an open GitHub repository with strong community adoption (64.7k stars), which materially lowers supply-chain risk. Although the license is unspecified, maintenance status is unknown, and the skill depends on external Composio/rube.app infrastructure, the current material does not show closed-source distribution, abandonment, or overtly suspicious packaging.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "GroqCloud Automation" skill from askskill: 1. Download https://raw.githubusercontent.com/ComposioHQ/awesome-claude-skills/master/composio-skills/groqcloud-automation/SKILL.md 2. Save it as ~/.claude/skills/groqcloud-automation/SKILL.md 3. Reload skills and tell me it's ready
Automate AI inference workflows using GroqCloud's ultra-fast API -- chat completions, model discovery, audio translation, and TTS voice selection -- all orchestrated through the Composio MCP integration.
Toolkit docs: composio.dev/toolkits/groqcloud
https://rube.app/mcpGROQCLOUD_* tools become available for executionList all models available on GroqCloud to find valid model IDs before running inference.
Tool: GROQCLOUD_LIST_MODELS
No parameters required -- returns all available models with metadata.
Use this as a prerequisite before any chat completion call to ensure you reference a valid, non-deprecated model ID.
Generate AI responses for conversational prompts using a specified GroqCloud model.
Tool: GROQCLOUD_GROQ_CREATE_CHAT_COMPLETION
| Parameter | Type | Required | Description |
|---|---|---|---|
model | string | Yes | Model ID from GROQCLOUD_LIST_MODELS |
messages | array | Yes | Ordered list of {role, content} objects (system, user, assistant) |
temperature | number | No | Sampling temperature 0-2 (default: 1) |
max_completion_tokens | integer | No | Max tokens to generate |
top_p | number | No | Nucleus sampling 0-1 (default: 1) |
stop | string/array | No | Up to 4 stop sequences |
stream | boolean | No | Enable SSE streaming (default: false) |
Retrieve detailed metadata for a specific model including context window and capabilities.
Tool: GROQCLOUD_GROQ_RETRIEVE_MODEL
| Parameter | Type | Required | Description |
|---|---|---|---|
model | string | Yes | Model identifier (e.g., groq-1-large) |
Translate non-English audio files into English text using Whisper models.
Tool: GROQCLOUD_GROQ_CREATE_AUDIO_TRANSLATION
| Parameter | Type | Required | Description |
|---|---|---|---|
file_path | string | Yes | Local path, HTTP(S) URL, or base64 data URL for audio |
model | string | No | Model ID (default: whisper-large-v3). Note: whisper-large-v3-turbo may not support translations |
response_format | string | No | json, verbose_json, or text (default: json) |
temperature | number | No | Sampling temperature 0-1 (default: 0) |
Enumerate available text-to-speech voices for Groq PlayAI models to drive voice selection UX.
Tool: GROQCLOUD_LIST_VOICES
Returns the set of supported TTS voices. Note: this is a static list maintained manually.
| Pitfall | Details |
|---|---|
| Nested model list | GROQCLOUD_LIST_MODELS response may be nested at response['data']['data'] -- do not assume a flat top-level array |
| Hard-coded model IDs break | Always fetch model IDs dynamically via GROQCLOUD_LIST_MODELS; hard-coded names can break when models are deprecated or renamed |
| Audio format validation | GROQCLOUD_GROQ_CREATE_AUDIO_TRANSLATION rejects invalid or unsupported audio formats silently -- validate inputs before calling |
| Model metadata drifts | Data from GROQCLOUD_GROQ_RETRIEVE_MODEL (context window, features) can change as models update -- do not treat it as static |
| TTS voice changes | Voice sets from GROQCLOUD_LIST_VOICES may shrink or rename over time -- handle missing voices gracefully |
| Tool Slug | Purpose |
|---|---|
GROQCLOUD_LIST_MODELS | List all available models and metadata |
…
Automate Carbone document generation and template workflows through Rube MCP.
Automate Echtpost workflows via Rube MCP after checking current tool schemas first.
Automate Castingwords transcription tasks and related workflows through MCP.
Automate Cats tasks through Rube MCP after checking the latest tool schemas.
Automate Cardly workflows through Rube MCP with tool schema discovery first.
Automate Certifier workflows via Rube MCP using current tool schemas first.
Automate ElevenLabs text-to-speech, voice management, and audio history workflows.
Retrieve and analyze Gong calls, transcripts, and conversation data with natural language.
Automate OpenAI API tasks for text, embeddings, images, and model listing.
Use Groq models via MCP clients for fast multimodal inference.
Manage Gumroad products, sales, license checks, and webhooks with natural language.
Search Groq API docs with natural language to find endpoints and usage fast.