Deepgram Speech-to-Text Automation Assistant
Paste the following prompt into your AI chat to install this skill:
Install @org-02qudk26/deepgram-automation in your AI assistant by following https://skillhub.cn/install/skillhub.md.
About this skill
Problem
Speech-to-text workflows often fail at three points: uncertain tool interfaces, unknown Deepgram connection status, and easy-to-miss parameter or pagination details. This skill targets environments already connected to Rube MCP and turns the Composio Deepgram toolkit into a discoverable, checkable, executable workflow instead of guessing tool names and fields.
How It Works
- Discover first: call
RUBE_SEARCH_TOOLSto get current tool slugs, input schemas, recommended execution plans, and known pitfalls. - Verify connection: use
RUBE_MANAGE_CONNECTIONSfor thedeepgramtoolkit and proceed only when status is ACTIVE. - Execute carefully: run discovered tools with
RUBE_MULTI_EXECUTE_TOOL; for bulk operations, useRUBE_REMOTE_WORKBENCHwithrun_composio_tool(). - Preserve context: reuse session IDs within one workflow and generate new ones for new workflows; follow pagination tokens until complete.
Boundary: it depends on Rube MCP and the Composio Deepgram toolkit, and does not replace a full Deepgram service integration. If the connection is inactive, schemas change, or private parameters are hardcoded, re-run discovery and validation first.
Use Cases
- Query current Deepgram transcription tools in a Rube MCP client and run a speech-to-text task.
- Before batch audio processing, confirm Deepgram connection is ACTIVE with `RUBE_MANAGE_CONNECTIONS`, then call discovered tools.
- After Deepgram tool schemas change, rerun `RUBE_SEARCH_TOOLS` to fetch fields and avoid failures from hardcoded slugs.
- When running multiple Composio Deepgram operations, execute them through `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`.
Best For
- Engineering teams integrating Deepgram transcription into MCP clients want fewer manual tool parameter updates.
- Backend engineers owning speech-to-text pipelines need stable tool discovery, connection checks, and batch execution.
- Integration engineers maintaining Composio tool connections need to handle auth activation, schema validation, and pagination.
- AI engineers building meeting or support-recording transcription apps want to route Deepgram capabilities through Rube MCP.
Related Skills
Uses step-by-step choices to confirm business, palette, and layout, then exports an editable .drawio architecture diagram.
An agent skill for the Miaoyin AI music REST API that supports SUNO/Mureka-based song generation, continuation, cover, video, WAV, and stem splitting.
Distills text, files, or images into structured knowledge and generates knowledge-card prompts for drawing tools, supporting 3:4 portrait or 16:9 landscape outputs.
Capture full-page, viewport, or element screenshots with Playwright while handling lazy loading, internal scroll, mobile layouts, and Linux CJK fonts.