Home › Prompts › Muse Spark Open (Meta, open weights) › Voice memo to a prioritized plan

Voice memo to a prioritized plan

Send a rambling voice memo straight to Muse Spark Open's audio input and get back decisions, tasks with owners and dates, and open questions.

Muse Spark Open (Meta, open weights)Personal productivityRuleStack original

Written for Muse Spark Open (meta-models/Muse-Spark-Open-816B-A42B) · Updated 2026-10-18

Note: Review and test before use. Provided as is, without warranty. See Terms.

The attached audio is my voice memo about [topic, e.g. next month's product launch]. Listen to all of it.

Give me:
1. A 3-sentence summary of what I'm trying to achieve.
2. Decisions I've already made (quote my words briefly).
3. Tasks: verb-first, with owner ([names or "me"]) and a date if I mentioned one, sorted by priority (must / should / could).
4. Open questions and risks I raised but didn't resolve.
5. One thing I seem to be forgetting, based on what I said.

Use my wording for names and terms. If a part of the audio is unclear, mark it [unclear at mm:ss] rather than guessing.

Replace everything in [square brackets] with your own details.

Settings & parameters

• Audio goes in as input (the processor expects mono 24 kHz and resamples for you through the chat template); output is text
• reasoning_effort low is enough for short memos; use medium for long or messy recordings
• Can run fully local (Meta reports it fits on two M5 Ultra Mac Studios via MLX), so private memos never leave your machines

Variations

• Meeting recording: add attendee names and ask for a follow-up email draft.
• Weekly review: attach several memos and ask for themes across them.

Tips

• Audio uses about 12.5 tokens per second, so an hour of audio is roughly 45,000 tokens of the 1M window.