Writing With Voice Assistants

In just a few minutes, here’s one thing you can do to make AI outputs 10x sharper. One of the most common reasons that prompts fail is not because they are too long, but because they lack personal context. And the fastest fix is to dictate your context. Speak for five to ten minutes about the problem, your audience, and the outcome you want, then paste the transcript into your prompt. Next, add your intent and your boundaries in plain language. For example: “I want to advocate for personal healthcare. Keep the tone empowering, not invasive. Do not encourage oversharing. Help people feel supported in the doctor’s office without implying that all responsibility sits on them.” Lastly, tell the model exactly what to produce. You might say: “Draft the first 400 words, include a clear call to action, and give me three title options.” Here’s a mini template: → State who you are and who this is for → Describe your stance and what to emphasize → Add guardrails for tone, privacy, and any “don’ts” → Set constraints like length, format, and voice → Specify the deliverable you want next Until AI memory reliably holds your details, you are responsible for supplying them. Feed the model your story - no need to include PII - to turn generic responses into work that sounds like you.

Voice AI is more than just plugging in an LLM. It's an orchestration challenge involving complex AI coordination across STT, TTS and LLMs, low-latency processing, and context & integration with external systems and tools. Let's start with the basics: ---- Real-time Transcription (STT) Low-latency transcription (<200ms) from providers like Deepgram ensures real-time responsiveness. ---- Voice Activity Detection (VAD) Essential for handling human interruptions smoothly, with tools such as WebRTC VAD or LiveKit Turn Detection ---- Language Model Integration (LLM) Select your reasoning engine carefully—GPT-4 for reliability, Claude for nuanced conversations, or Llama 3 for flexibility and open-source options. ---- Real-Time Text-to-Speech (TTS) Natural-sounding speech from providers like Eleven Labs, Cartesia or Play.ht enhances user experience. ---- Contextual Noise Filtering Implement custom noise-cancellation models to effectively isolate speech from real-world background noise (TV, traffic, family chatter). ---- Infrastructure & Scalability Deploy on infrastructure designed for low-latency, real-time scaling (WebSockets, Kubernetes, cloud infrastructure from AWS/Azure/GCP). ---- Observability & Iterative Improvement Continuous improvement through monitoring tools like Prometheus, Grafana, and OpenTelemetry ensures stable and reliable voice agents. 📍You can assemble this stack yourself or streamline the entire process using integrated API-first platforms like Vapi. Check it out here ➡️https://bit.ly/4bOgYLh What do you think? How will voice AI tech stacks evolve from here?

Cold email hack: Write with your voice 👇 I imagine you're a lot like me... You probably talk way more than you write. And your written voice sounds nothing like your speaking voice. For most cold emails, I'll speak them instead of write them. Here's why: ✅ I write great emails in half the time ✅ "Editing" feels way easier than "writing" ✅ Emails sound way more conversational (like it would on the phone) ✅ I never get writer's block Here's how to do this: Method 1: Set up dictation on your Mac - Open System Settings → Keyboard - Scroll down to Dictation - Turn Dictation on and set up a keyboard shortcut - Now you can speak text anywhere (like your sales engagement tool) Method 2: Speak to voice inside of Google Docs Biggest con here is it'll only work inside of Google Docs - Open a Google Doc - Put your cursor where you want to type the text - Go to Tools → Voice Typing (or hold down Shift + Command + S) - Now you can speak text anywhere inside the doc ~~~ Give this a try, and you'll be blown away by how fast you can write great emails. Have you tried this method before?

I haven't typed a full paragraph in months. Most founders are still grinding out content the hard way. Meanwhile, I'm creating more efficiently using voice and AI systems. Content creation shouldn't come with burnout. Here's how I create 30 pieces instead: 1. Voice-First Creation I speak my ideas instead of typing them. Voice is faster than fingers and captures natural conversational flow. AI transcription tools turn my thoughts into polished content instantly. 2. The 3-Tool Content Engine Tool 1: Voice recorder for raw idea capture during walks or commutes. Tool 2: AI transcription that turns speech into structured drafts. Tool 3: Content optimization AI that adapts one idea across multiple platforms. 3. The Secret Content Checklist Before any content goes live, it passes through 5 systematic checks. Hook strength, value delivery, platform optimization, engagement triggers, and call-to-action clarity. Quality control happens through systems, not hope. 4. Content Multiplication System One 10-minute voice recording becomes 30+ pieces of content. LinkedIn posts, Twitter threads, YouTube scripts, newsletter sections. Each optimized for its platform while maintaining core message integrity. 5. Batch Production Days I record all content in focused 2-hour sessions. Then AI handles the heavy lifting of adaptation and optimization. Creation becomes systematic instead of reactive. The result: Content creation that scales without burning out the creator. Most founders create content. I systematize content production. Your voice is your competitive advantage. AI can optimize and multiply, but it can't replace your unique perspective and experience. Stop typing yourself into burnout. Start speaking your content into existence. __ Enjoy this? ♻️ Repost it to your network and follow Matt Gray for more. Want to learn how to create content the easy way? Get my free AI course that shows you the systems that helped me scale my businesses with AI automation. Join here: https://lnkd.in/eVfUj42h 

Gmail’s AI email assistant writes like a committee of lawyers designed it. Pete Koomen’s recent post Horseless Carriages explains why: developers control the AI prompts instead of users. In his post he argues that software developers should expose the prompts and the user should be able to control it. He inspired me to build my own. I want a system that’s fast, accounts for historical context, & runs locally (because I don’t want my emails to be sent to other servers), & accepts guidance from a locally running voice model. Here’s how it works: 1. I press the keyboard shortcut, F2. 2. I dictate key points of the email. 3. The program finds relevant emails to/from the person I’m writing. 4. The AI generates an email text using my tone, checks the grammar, ensures that proper spacing & paragraphs exist, & formats lists for readability. 5. It pastes the result back. Here are two examples : emailing a colleague, Andy (https://lnkd.in/gtjt3BPp), & a hypothetical founder (https://lnkd.in/gDwM4f22). Instead of generics, the system learns from my actual email history. It knows how I write to investors vs colleagues vs founders because it’s seen thousands of examples. The point isn’t that everyone will build their own email system. It’s that these principles will reshape software design. - Voice dictation feels like briefing an assistant, not programming a machine. - The context layer - that database of previous emails - becomes the most valuable component because it enables true personalization. - Local processing, voice control, & personalized training data could transform any application, not just email, because the software learns from my past uses We’re still in the horseless carriage era of AI applications. The breakthrough will come when software adapts to us instead of forcing us to adapt to it. Centered around a command line email client called Neomutt (https://neomutt.org/). The software hits LanceDB, a vector database with embedded emails & finds the ones that are the most relevant from the sender to match the tone. The code is here (https://lnkd.in/gZ-AaAWa).

𝗡𝗮𝘃𝗶𝗴𝗮𝘁𝗶𝗻𝗴 𝘁𝗵𝗲 𝗗𝗮𝘁𝗮 𝗣𝗿𝗶𝘃𝗮𝗰𝘆 𝗠𝗮𝘇𝗲 𝘄𝗶𝘁𝗵 𝗩𝗼𝗶𝗰𝗲 𝗔𝘀𝘀𝗶𝘀𝘁𝗮𝗻𝘁𝘀 Voice assistants have undoubtedly transformed the way we interact with technology, making tasks more convenient and efficient. However, as we embrace this innovation, we must also be vigilant about the data privacy concerns it raises. The convenience of voice commands often means sharing personal information with these assistants. This includes everything from shopping preferences to calendar events. It's essential to recognize the following privacy concerns: 🎙 Data Collection: Voice assistants record and store voice data, raising questions about who has access to this information and for what purposes. 🔍 Eavesdropping: There have been instances where voice assistants activate unintentionally, potentially listening to private conversations. Ensuring your assistant isn't recording when you don't intend it to is crucial. 🤖 Third-Party Integration: Voice assistants often integrate with third-party apps and services, which can result in data being shared across platforms. 🔒 Security Measures: Are the security measures in place robust enough to protect your voice data from unauthorized access or breaches? As professionals, we must prioritize data privacy in the digital age. Have you checked the settings of your voice assistants?

Typing memos about patient-doctor encounters into EHRs is so time-consuming that the demand for medical scribes has grown exponentially in the last couple of years. That alone still cannot solve the problem that half of physicians’ average workdays are spent conducting clerical work and administration. AI-based voice-to-text technologies promise to turn the tables: the doctor and the patient speak while a voice assistant listens in and puts down the interpreted text into the relevant columns in the EHRs. Sounds like science fiction? That’s no longer the case. We looked around where the technology stands today and how it could cure ‘desktop medicine’ in the future.

Over the last 6 months, I’ve been trying to train ChatGPT to write like me, and it’s time I shared my learnings. It is still nowhere near perfect, but it gives me a good draft for my work. Here are the 8 steps to do it yourself: 1️⃣ Start a New Chat and Promote ChatGPT Start by creating a new chat in ChatGPT that will be your virtual writing assistant throughout the training process. Prompt ChatGPT to tell it your goal and the process you want to follow. I've provided a sample prompt in the comments below. 2️⃣ Feed in Your Favorite Writing Samples The next step is to provide ChatGPT with your favorite writing samples. These can be articles, blog posts, or any content that reflects your unique style and tone. By doing so, ChatGPT will get a sense of your writing preferences. Quick tip: If you use different styles, e.g. for work vs a personal blog, consider training two different writing styles. 3️⃣ Ask ChatGPT to Describe Your Writing and Correct Any Errors If you used the above prompt, ChatGPT should describe your writing style. Encourage it to point out any errors or inconsistencies it identifies. This step helps ChatGPT understand your writing at a deeper level. If you disagree with how ChatGPT describes your style, correct it. 4️⃣ Repeat with at Least Five Writing Samples To refine ChatGPT's understanding of your writing, repeat steps 2 and 3 with at least five different writing samples. The more varied the content, the better ChatGPT can grasp your unique style. 5️⃣ Ask ChatGPT to Write Its First Draft Once ChatGPT has a good grasp of your writing style, ask it to write a draft in your voice. Provide it with bullet points to outline your thought and the argument you are trying to make, and let it work its magic. The first draft will likely be a bit rough, but that leads us to the next step. 6️⃣ Manually Edit the Draft Review the draft carefully for tone, style and accuracy, then make edits until you are happy with the draft. This step is crucial to fine-tune ChatGPT's writing. You'll be refining and molding its output to align more closely with your style. 7️⃣ Feed the Final Draft Back into ChatGPT After you've polished the draft, feed it back into ChatGPT. This step helps the AI understand the revisions you've made and further refines its understanding of your style. 8️⃣ Continually Refine Over Time Training ChatGPT is an ongoing process. Continue to co-author articles or documents over time by repeating steps 5 to 7 with new writing prompts and topics. The more you do this, the better ChatGPT becomes at mimicking your writing style. Have you tried anything similar? Are there better tools to use than ChatGPT that do this better? Let’s chat in the comments below. Next week, I’ll discuss how I’ve used this and other hacks to partially automate my broader writing process. Follow me here if you want to be sure to see when that is published. #AI #Productivity #FutureofWork #WritingTips

Generative AI can write content, poems, code...and...leak your secrets too! Improving productivity comes with hidden risks for CISOs. A Menlo Security Inc. study shows that 55% of entries into generative AI sites included Personally Identifiable Information (PII). When users interact with tools like ChatGPT or other AI platforms, they might unintentionally share PII or confidential data. From casual queries to sharing snippets of proprietary code, these leaks could cost businesses millions in compliance fines & reputation damage. Because AI doesn’t know what NOT to remember. Here are some common AI-driven leakages: 1) Generative AI querying: Employees use AI tools for drafting emails or reports but paste sensitive data into prompts, unaware it’s stored or analyzed by the tool. 2) Code suggestions: Developers share proprietary code to debug or optimize, risking the exposure of algorithms, intellectual property, or vulnerabilities. 3) Customer support inputs: Teams input real client data while training AI-based support tools, accidentally leaking customer information. 4) Content generation: Marketing teams upload drafts containing confidential product launches or sales strategies to AI-powered writing tools. 5) Browser extensions / integrations: AI-powered browser extensions analyze user activity and may capture sensitive browsing behavior or organizational data. 𝗕𝗿𝗼𝘄𝘀𝗲𝗿 𝗦𝗲𝗰𝘂𝗿𝗶𝘁𝘆 𝗵𝗲𝗹𝗽𝘀 𝗖𝗜𝗦𝗢𝘀 𝗮𝗰𝗵𝗶𝗲𝘃𝗲 𝗿𝗲𝘀𝗽𝗼𝗻𝘀𝗶𝗯𝗹𝗲 𝗔𝗜 𝘂𝘀𝗮𝗴𝗲. Here are 5 key advantages of Browser Security for AI: 1) Browser isolation: Solutions like Menlo Security prevent direct interaction between the user’s environment and AI tools by isolating AI sessions in the cloud. This eliminates the risk of unintended data sharing. 2) Browser data loss prevention (DLP): Enforce browser-based policies that block users from pasting sensitive data into AI tools. 3) Contextual monitoring: Advanced analytics track and flag risky behaviors, like uploading confidential files to AI platforms. 4) Extension whitelisting: Allow only verified AI browser extensions to run, ensuring unauthorized tools don’t extract sensitive information. 5) Content disarm & reconstruction (CDR): Strip out sensitive metadata from uploaded files before they reach generative AI platforms, neutralizing risks. Generative AI is both innovative & risky, depending on the use-cases. With browser security, you’re protecting your people + their endpoints + keeping your secrets safe from prying algos. If you're a CISO who's business users need to use AI securely, we can help you protect intentional / unintentional leakage of critical information via the browser. At runtime. We partner with Menlo Security Inc. to architect browser security for your organization. DM me for a 45-min. discovery call. ---- Hi! I’m Rajeev Mamidanna. I help Mid-market CISOs strengthen Cybersecurity Strategies + Build Authority on LinkedIn.

I HATE Writing & procrastinate till the last minute But AI speech-to-text rewired me—never going back Here’s 3 ways I use it: These tools are game-changers—here’s how I use them (and will share my faves below): 1️⃣ FIRST DRAFTS WITHOUT THE DREAD Tricky posts or emails that needed some thought used to stall me for hours. Now, I just hit record and let my messy, half-formed thoughts spill out. The AI transcribes my speech & then cleans it up into a 1st draft. To prevent AI from adding its cliched ideas & cringe voice, I have put instructions that tell it to preserves my points & voice. Now I have a 1st draft based on my original ideas, in my authentic voice that I can edit. Sometimes I end up editing 70% of that 1st draft. But I still find editing my 1st draft way easier than typing it in the first place. Result → Procrastination’s down, speed’s up, and I’m actually enjoying the process. 2️⃣ FRICTIONLESS REPLIES ****Like most people I have a lot of messages to reply to: Emails, Whatsapp, Linkedin comments, DMs — I want to do a good job with them but there are too many & they just keep coming. Earlier, I would just get overwhelmed every other day & give up. But not anymore! Here’s my workflow: → I open the communication app on my computer → I press the reply button & then hit a keyboard shortcut to start my Speech to Text app in the background → I speak my reply & hit the shortcut again → Boom! Clean text based on my speech appears exactly where my cursor is → No typing, no switching windows, no copy-paste This removal of friction has transformed my relationship with my inbox. Everyday I look forward to clearing it. I am able to write thoughtful and detailed replies. And I have never been more on top of my inbox. Clearing my inbox now almost feels like a game — a game that I can now win. 3️⃣ ACTIVE LEARNING COMPANION Whenever I am learning something, I now split my screen: → Content on one side (text, audio video) → Notes on the other Then after I consume a bit of the content, I pause, hit the shortcut for my speech-to-text app & articulate in my own words what I learnt. This has 2 benefits: → This articulation serves as a ‘Check for Understanding’. If I stumble then I immediately know what I don’t understand → If I have understood correctly, then my words get converted to text & now I have notes in MY words, not just text I have pasted without understanding. These tools don't just make me more efficient—they've fundamentally changed how I think and process information. It feels like I have super-powers & have broken free of the chains that would hold me back everyday. — — — Any AI tools you can’t live without?