Like many people, I do a lot of voice notes because talking is simply faster than typing.
As an Asana user, I ran into a major productivity bottleneck: I’d send an audio message into Slack or WhatsApp, and the actual action items would quickly get buried and forgotten. To fix this, I spent a couple of hours building a Make scenario that transforms raw voice notes into structured, context-aware tasks in Asana.
By utilizing Asana’s official Model Context Protocol (MCP) server alongside Make’s AI agent capabilities, the integration behaves like a smart, context-aware project manager and exec assistant.
It feels like absolute magic when you see it run for the first time.
How the Workflow Works
-
The Trigger: A new audio file is received in Make from communication tools like Slack, WhatsApp, or Telegram. ( I did this with a Slack bot. Definitely doable with others as well)
-
The Transcription: The audio file is downloaded and processed through an AI transcription module.
-
The “Brain”: The raw transcript passes to a Make AI Agent module equipped with a system prompt that extracts the core intent, identifies the assignee, and handles dynamic due dates (like turning “by next Monday” into an actual calendar timestamp).
-
The Routing via MCP: Instead of relying on manual hardcoded mappings, the AI agent interacts with the workspace using the Asana MCP server. The AI semantically routes the data to the exact project, section, and assignee and due date based entirely on the context of the speech.
Real-World Results
Instead of opening a project management tool and clicking through endless dropdowns, it takes 10 seconds of speech, and the Make and MCP handles the rest.
“Hey, there’s a bug on the checkout button.”
Result: Instantly lands in the Engineering project under the Bugs section, assigned to the appropriate developer.
“We need a promo video ready by next Monday.”
Result: Automated creation in the Marketing project under the Creative section, assigned to the video editor with the correct due date set.
Bridging the Executive Gap
This setup is a game-changer for senior executives who don’t want to log in and manually assign things, as well as team members who prefer working entirely within their project spaces. The execs can just talk, and the team gets structured work inside the environment they prefer. It is a win-win for everyone.
Pro-Tips for Implementation
-
Leverage Native Capabilities: Combine native Asana module features with Make to build tighter loops and optimize your operations.
-
Optimize Your Models: Start with a higher-tier LLM model inside your scenario to map out complex routing and prompt nuances, then optimize down to smaller models once your logic is stable.
-
Leverage Built-in Tools: Using Make’s native AI capabilities and direct MCP integration heavily streamlines your setup, reducing the need to manually code complex API calls or handle multiple external tokens.
Would love to know other MCP use cases you guys are building.