Turn a rambling voice note into professional English.
Say it any way it comes out. Have AI find the message inside the detours and turn it into writing you would actually send.
Try it now
Copy the prompt into your AI tool of choice, then answer its questions as they come.
Paste it into any AI chat to start. For most people, this is all you need.
Everything on this page in one paste: the prompt plus the full plan, every step and what to check. Use it for longer moves, to plan ahead, to share with a colleague, or if your AI can't open links.
How it goes
What the AI will do
- Turn your spoken thoughts into clear writing for the intended reader, using relevant correspondence and project context.
What to have ready
- A voice note or transcript; an audience or intended use if you already have one.
Where you come in
- Clarify uncertain meaning, choose a useful tone or format, and check that the result sounds like you.
What you'll get
You have a polished message or document that preserves your intended meaning and voice, with any unresolved factual details clearly identified.
You're done when
You have a polished message or document that preserves your intended meaning and voice, with any unresolved factual details clearly identified.
These are general instructions, not a description of this user's particular AI system, tools, access, or circumstances. Adapt the method to the user's goal and the capabilities you can actually use, while preserving the activity's essential sequence, review points, and intended result. ### Start with the activity and the user's context Read the complete activity and guide the user through it. Use the activity prompt yourself; the user does not need to paste it again. Keep the responsibilities of the user, the AI, and any colleague clear. Begin with what the user has already supplied. Establish the intended result and resolve missing context through focused questions when needed. Work within the activity's stated scope, permissions, required confirmations, and stopping points, including any deliberate order for introducing information. Make progress with the available information and reasonable, clearly identified assumptions where the activity allows them. ### Check the capabilities needed for this work Inspect relevant available tools, connectors, and data. Use small, relevant, non-destructive checks to establish whether necessary access or a capability actually works. Naming a product does not establish access to it. Let this activity determine what needs checking; do not impose a universal preliminary questionnaire or a full system audit. When useful access is missing: - Explain what you cannot reach and how that material would help. - Investigate practical setup, connection, export, or other access alternatives before asking the user to gather material or troubleshoot. - If progress depends on access, request only the specific user action or permission needed to enable it or provide the material another way. Continue useful independent work while awaiting the response. - Offer to walk the user through an export or upload. Welcome files, links, copied text, rough notes, or an interview as supported by your system and the activity, and use the best available route. If the missing access is optional, continue with what is available. ### Ask focused questions and respect the answers Ask questions only when necessary to complete the work well or satisfy the activity's required review points. Build on answers already supplied. Ask one question at a time, or a small group of closely related questions. Wait on work that depends on the answer, and continue useful work that does not. Explain unfamiliar language with examples where helpful. Confirm answers or decisions you supply on the user's behalf before treating them as the user's final answers or decisions. This does not require separate approval of every sourced finding; follow the activity's specific review requirements. ### Keep evidence and independent contributions distinct Distinguish evidence, inference, and missing information. Check your work against the source material. Use independent agents when your system actually supports delegation and independent investigation or review would improve the work: - Give each agent a bounded brief and the context appropriate to its role. - Keep discovery independent until synthesis where the activity requires it. Preserve any requirement for the user or colleagues to contribute before seeing other explanations. - Follow the activity's stated fallback and any required confirmation when independent agents or fresh contexts are unavailable. Preserve reviewer isolation where required; describe shared-context or sequential passes accurately. ### Produce, check, and revise the result Do the substantive investigation and production. Carry the activity through to the most complete, usable result within its scope, rather than ending with a plan or handing the main work back to the user. When missing information does not prevent useful work, proceed with clearly identified assumptions where the activity permits them. Check the result against the activity's completion criteria. At each substantive delivery, state what is complete and any material unfinished work, assumptions, helpful missing information, and remaining uncertainty. Explain how these affect what the user can use, and help the user revise the result. Preserve the activity's stopping point. Do not turn a rehearsal, investigation, or test-design activity into execution that the user has not authorized. Turn my rambling voice note into clear professional English while preserving what I mean and how I sound. ### 1. Listen for the message and establish its purpose. Read or listen to what I supplied. Check your ability to access and transcribe the recording. If necessary, help me obtain a transcript or share the material in a supported form. Do not reconstruct words you could not hear as though they were certain. Identify the main point, supporting facts, requested action, audience, and emotional tone. Separate false starts and repetition from qualifications or distinctions that matter. Use names, projects, and issues in the note to search relevant available email, messages, chats, meeting transcripts, documents, and project files. Look for the prior exchange, terminology, or promised next step that would help this particular message. Keep additions from those sources distinguishable while drafting. Ask a focused question when purpose, audience, or an uncertain phrase would change the result, and wait for the answer before relying on it. If two treatments would be useful, offer concrete alternatives such as a short email with a direct request or a fuller explanatory note. Explain their difference and help me choose; otherwise proceed with the evident purpose. ### 2. Write the piece. Lead with what the reader needs to understand or do. Organize supporting material in a sensible sequence, remove verbal clutter, and use natural sentences. Preserve useful examples, my level of certainty, and the strength of my intended point. Professional English can be warm and direct; do not flatten personality into corporate language. - Check factual additions against the sources you actually read. - Do not invent commitments, reasons, quotations, or details to make the writing flow. - Ask about a consequential gap, or use a clearly marked placeholder for a minor detail that can be filled later. - If my spoken account contradicts the surrounding correspondence, raise the conflict rather than silently choosing a version. ### 3. Check and finish. Compare the draft with the recording or transcript: have you preserved the central meaning, important nuance, and intended action? Check names, numbers, dates, and quoted wording. Read it from the recipient’s perspective for clarity. Present the usable draft first, with only the questions or brief explanation needed to assess it. Invite corrections to meaning or voice and revise if I supply them. Deliver it as text or an editable file suited to its intended use. Finish with a ready-to-use draft and clearly identified remaining details; this activity does not send the message. These instructions were written in September 2026 using the frontier models available at the time. You may now have better tools or models, or restrictions that make some tasks harder. Your AI should adapt to the tools and access you actually have and find the best available way to help. Everything here is a starting suggestion for you and your AI, not a proven best practice for every setup. Feel free to rewrite any of it to better meet your needs.
View full AI instructions
Turn a rambling voice note into professional English.
What the AI will do
- Turn your spoken thoughts into clear writing for the intended reader, using relevant correspondence and project context.
What you can provide
- A voice note or transcript; an audience or intended use if you already have one.
Where you'll take part
- Clarify uncertain meaning, choose a useful tone or format, and check that the result sounds like you.
What you'll get
You have a polished message or document that preserves your intended meaning and voice, with any unresolved factual details clearly identified.
Activity context
Say it any way it comes out. Have AI find the message inside the detours and turn it into writing you would actually send.
For the user
Share a voice note, recording, or rough transcript. Related correspondence can help the AI understand names, references, and why you are writing. You’ll clarify any uncertain meaning and choose between approaches if two would serve different purposes.
Guidance for the AI
These are general instructions, not a description of this user's particular AI system, tools, access, or circumstances. Adapt the method to the user's goal and the capabilities you can actually use, while preserving the activity's essential sequence, review points, and intended result.
Start with the activity and the user's context
Read the complete activity and guide the user through it. Use the activity prompt yourself; the user does not need to paste it again. Keep the responsibilities of the user, the AI, and any colleague clear.
Begin with what the user has already supplied. Establish the intended result and resolve missing context through focused questions when needed. Work within the activity's stated scope, permissions, required confirmations, and stopping points, including any deliberate order for introducing information. Make progress with the available information and reasonable, clearly identified assumptions where the activity allows them.
Check the capabilities needed for this work
Inspect relevant available tools, connectors, and data. Use small, relevant, non-destructive checks to establish whether necessary access or a capability actually works. Naming a product does not establish access to it. Let this activity determine what needs checking; do not impose a universal preliminary questionnaire or a full system audit.
When useful access is missing:
- Explain what you cannot reach and how that material would help.
- Investigate practical setup, connection, export, or other access alternatives before asking the user to gather material or troubleshoot.
- If progress depends on access, request only the specific user action or permission needed to enable it or provide the material another way. Continue useful independent work while awaiting the response.
- Offer to walk the user through an export or upload. Welcome files, links, copied text, rough notes, or an interview as supported by your system and the activity, and use the best available route. If the missing access is optional, continue with what is available.
Ask focused questions and respect the answers
Ask questions only when necessary to complete the work well or satisfy the activity's required review points. Build on answers already supplied. Ask one question at a time, or a small group of closely related questions. Wait on work that depends on the answer, and continue useful work that does not. Explain unfamiliar language with examples where helpful.
Confirm answers or decisions you supply on the user's behalf before treating them as the user's final answers or decisions. This does not require separate approval of every sourced finding; follow the activity's specific review requirements.
Keep evidence and independent contributions distinct
Distinguish evidence, inference, and missing information. Check your work against the source material.
Use independent agents when your system actually supports delegation and independent investigation or review would improve the work:
- Give each agent a bounded brief and the context appropriate to its role.
- Keep discovery independent until synthesis where the activity requires it. Preserve any requirement for the user or colleagues to contribute before seeing other explanations.
- Follow the activity's stated fallback and any required confirmation when independent agents or fresh contexts are unavailable. Preserve reviewer isolation where required; describe shared-context or sequential passes accurately.
Produce, check, and revise the result
Do the substantive investigation and production. Carry the activity through to the most complete, usable result within its scope, rather than ending with a plan or handing the main work back to the user. When missing information does not prevent useful work, proceed with clearly identified assumptions where the activity permits them.
Check the result against the activity's completion criteria. At each substantive delivery, state what is complete and any material unfinished work, assumptions, helpful missing information, and remaining uncertainty. Explain how these affect what the user can use, and help the user revise the result.
Preserve the activity's stopping point. Do not turn a rehearsal, investigation, or test-design activity into execution that the user has not authorized.
Your AI prompt
Turn my rambling voice note into clear professional English while preserving what I mean and how I sound.
1. Listen for the message and establish its purpose.
Read or listen to what I supplied. Check your ability to access and transcribe the recording. If necessary, help me obtain a transcript or share the material in a supported form. Do not reconstruct words you could not hear as though they were certain.
Identify the main point, supporting facts, requested action, audience, and emotional tone. Separate false starts and repetition from qualifications or distinctions that matter. Use names, projects, and issues in the note to search relevant available email, messages, chats, meeting transcripts, documents, and project files. Look for the prior exchange, terminology, or promised next step that would help this particular message. Keep additions from those sources distinguishable while drafting.
Ask a focused question when purpose, audience, or an uncertain phrase would change the result, and wait for the answer before relying on it. If two treatments would be useful, offer concrete alternatives such as a short email with a direct request or a fuller explanatory note. Explain their difference and help me choose; otherwise proceed with the evident purpose.
2. Write the piece.
Lead with what the reader needs to understand or do. Organize supporting material in a sensible sequence, remove verbal clutter, and use natural sentences. Preserve useful examples, my level of certainty, and the strength of my intended point. Professional English can be warm and direct; do not flatten personality into corporate language.
- Check factual additions against the sources you actually read.
- Do not invent commitments, reasons, quotations, or details to make the writing flow.
- Ask about a consequential gap, or use a clearly marked placeholder for a minor detail that can be filled later.
- If my spoken account contradicts the surrounding correspondence, raise the conflict rather than silently choosing a version.
3. Check and finish.
Compare the draft with the recording or transcript: have you preserved the central meaning, important nuance, and intended action? Check names, numbers, dates, and quoted wording. Read it from the recipient’s perspective for clarity.
Present the usable draft first, with only the questions or brief explanation needed to assess it. Invite corrections to meaning or voice and revise if I supply them. Deliver it as text or an editable file suited to its intended use. Finish with a ready-to-use draft and clearly identified remaining details; this activity does not send the message.
Done when
You have a polished message or document that preserves your intended meaning and voice, with any unresolved factual details clearly identified.
These instructions were written in September 2026 using the frontier models available at the time. You may now have better tools or models, or restrictions that make some tasks harder. Your AI should adapt to the tools and access you actually have and find the best available way to help. Everything here is a starting suggestion for you and your AI, not a proven best practice for every setup. Feel free to rewrite any of it to better meet your needs.
These instructions were written in September 2026 using the frontier models available at the time. You may now have better tools or models, or restrictions that make some tasks harder. Your AI should adapt to the tools and access you actually have and find the best available way to help. Everything here is a starting suggestion for you and your AI, not a proven best practice for every setup. Feel free to rewrite any of it to better meet your needs.