iTechGuides is reader-supported. When you buy through links on our site, we may earn an affiliate commission. As an Amazon Associate I earn from qualifying purchases. Learn more
saymd turns a spoken coding request or audio file into a structured Markdown prompt that an AI coding agent can reference. Instead of dropping an unedited transcript into a chat box, the free MIT-licensed command-line tool produces a file such as .ai/prompt.md, organized around objectives, context, instructions, and constraints. You then point ChatGPT/Codex or another supported coding agent at that file with its normal file-reference syntax. Viktor Kondas, saymd’s creator, describes the workflow as “Speak once, get a Markdown prompt any agent can @.”
This guide explains the setup, recording flow, templates, provider keys, privacy claims, Free and Pro editions, and the plugin surfaces documented by the project. Availability and limits can change, so treat marketplace listings, model IDs, recording caps, and prices as time-sensitive project information rather than independently verified test results.
What does saymd do that ordinary voice dictation does not?
saymd is designed to create a usable specification, not merely a transcript. You speak a feature request, bug report, implementation plan, or other coding requirement; a speech-to-text provider transcribes it; and the tool turns that material into Markdown with sections an agent can follow.
The project README puts the distinction plainly: “The raw transcript is not the main artifact — the structured spec is.” That structure gives an agent an explicit objective and boundaries before it starts changing code. The resulting file is portable: any coding tool that can read or reference Markdown can consume it, rather than requiring a special chat history or a particular editor.
#1 Best Overall
- Read Before You Buy — No Video Output: These adapters support charging and USB 2.0 data transfer, but cannot transmit video signals. Except for standard USB webcams (which use USB data only), they are not compatible with HDMI/DisplayPort cables, video-capable USB-C hubs, or docking stations with video output.
- Convert USB-A Ports to USB-C: Designed to connect USB-C earphones, cables, flash drives, card readers, and other USB-C accessories to standard USB-A ports. Plug-and-play with no drivers or software required.
- Aluminum Alloy Housing: Built with a sturdy aluminum alloy shell that aids in heat dissipation and protects against daily wear and scratches. Designed to maintain a stable and secure connection.
- Compact & Travel-Friendly: The ultra-compact design allows the adapter to stay plugged into your device without blocking adjacent ports or adding bulk, reducing wear and tear on your original USB ports.
- 12-Month Warranty: Backed by a 12-month manufacturer warranty for peace of mind. Designed to meet strict quality control standards for reliable everyday performance.
The basic loop
- Record from your microphone or supply an existing audio file.
- Let the selected provider transcribe the speech. Gemini and OpenAI are documented as also helping structure the Markdown; Deepgram and ElevenLabs handle transcription and need a Gemini or OpenAI key for the structuring step.
- Write the generated specification to
.ai/prompt.mdor another path you choose. - Reference that file in your AI coding agent and ask the agent to implement, investigate, or plan against it.
The separation between capture and execution is useful when requirements are easier to say than type. You can keep the prompt file with the project, review its wording, and edit constraints before an agent acts.
How do I install and run saymd?
On a supported machine, the documented quick start is three commands: run setup, check prerequisites with doctor, then launch the recorder. The repository also shows a pinned package invocation so you can reproduce a specific published version.
- Install Node.js 20 or newer and
ffmpeg. The project documents macOS and Linux as supported environments. On Windows, it describes WSL or file-input use rather than a native microphone workflow. - Run
npx saymd setup. This initializes the local configuration flow. - Run
npx saymd doctor. The diagnostic checks forffmpeg, a usable microphone, the selected provider, and the required API key. - Start an interactive recording with
npx saymd. - When you want a pinned example, use
npx saymd@0.1.2, the version shown in the README, and review the generated.ai/prompt.md.
Use doctor before troubleshooting the agent itself. If it reports a missing executable, install or expose ffmpeg on your PATH; if it reports a provider or key problem, fix the account configuration before recording again.
Windows Errors? Fix Them Before They Spread
Repair common Windows errors and clear accumulated junk for a smoother, more stable PC - no reinstall needed.Free scan · no reinstallCrashes, No Sound, or Screen Glitches?
Random freezes, missing sound and display glitches usually trace back to one bad driver. Find and replace yours safely.Free scan · under a minuteCan I use an existing recording?
Yes. The CLI accepts an audio file with --file. The README lists mp3, m4a, wav, ogg, opus, flac, webm, aiff, caf, mp4, and mov among the accepted formats. This is also the documented Windows route when you do not use WSL’s microphone access.
Which command-line options shape the prompt?
The main options let you choose the source, template, recording length, language, provider, and destination without changing the project files.
| Option | Purpose | Example |
|---|---|---|
--file |
Transcribe an existing audio file instead of recording live. | npx saymd --file meeting.m4a |
--template |
Choose a structure for a feature, bug, plan, or the default prompt. | npx saymd --template feature |
--seconds |
Set the live recording duration within the edition’s documented limits. | npx saymd --seconds 45 |
--lang |
Supply the spoken-language setting when you do not want to rely on automatic detection. | npx saymd --lang en |
--provider |
Select the speech provider configured with your own key. | npx saymd --provider gemini |
-o |
Write the Markdown to a custom output path. | npx saymd -o .ai/feature.md |
Combine these flags when a recording needs a particular shape and location, for example a bug template written to a branch-specific prompt file. The exact model availability behind a provider can change, so use the provider and package documentation shown by your installed version when a command is rejected.
Rank #2
- 5-in-1 USB-C Hub: Experience comprehensive connectivity featuring a Power Delivery input, two USB-A 2.0 ports, a USB-A 3.0 port, and an HDMI port. (Note: The USB-C power delivery input port is only for connecting an external wall charger to power your laptop and cannot power peripheral devices.)
- 90W Pass-Through Charging: Achieve optimal charging with 90W pass-through power to your laptop, supported by a total input of 100W, with the hub reserving 10W for operational efficiency. (Note: Wall charger not included.)
- Quick Data Transfers: Accelerate your productivity with rapid data transfers using a high-speed 5Gbps USB 3.0 port and two 480Mbps USB 2.0 ports.
- 4K HDMI Display: Enhance your visual experience with a hub capable of delivering 4K resolution at 30Hz in both mirror and extend modes. Please note that this hub is compatible with MacBook (macOS 12 and newer), Windows 10 and 11, ChromeOS, and laptops equipped with DP Alt Mode and Power Delivery. Note: This device is not compatible with Linux.
- What You Get: Anker USB-C Hub (5-in-1, 4K HDMI), welcome guide, 18-month warranty, and our friendly customer service.
What does each saymd template include?
The template controls the headings the structuring step aims to fill. Without a template, saymd uses a general specification suitable for a short requirement.
Default
The default headings are Objective, Context, Instructions, and Constraints. This is the broadest choice when your speech mixes background, desired behavior, and implementation boundaries.
Feature
The feature template adds Acceptance criteria. Use it when the agent needs a definition of done that can be checked after implementation, not just a description of the desired capability.
Bug
The bug template provides Steps to reproduce and Expected / Actual. Those headings separate the observed failure from the behavior you intended, which reduces the chance that an agent treats a symptom as the requirement.
Plan
The plan template uses numbered Steps and Open questions. It is appropriate when you want an implementation sequence or investigation plan before asking for code changes.
Do these 3 things before closing this tab:
1Clear out junk files and repair common Windows errors2Scan for outdated or missing drivers - takes under a minute3Repair Windows errors before they cause bigger problemsTemplates do not replace your review. Listen for missing versions, edge cases, file names, permissions, or acceptance conditions in the generated Markdown and edit the file before invoking an agent.
Rank #3
- Sleek 7-in-1 USB-C Hub: Features an HDMI port, two USB-A 3.0 ports, and a USB-C data port, each providing 5Gbps transfer speeds. It also includes a USB-C PD input port for charging up to 100W and dual SD and TF card slots, all in a compact design.
- Flawless 4K@60Hz Video with HDMI: Delivers exceptional clarity and smoothness with its 4K@60Hz HDMI port, making it ideal for high-definition presentations and entertainment. (Note: Only the HDMI port supports video projection; the USB-C port is for data transfer only.)
- Double Up on Efficiency: The two USB-A 3.0 ports and a USB-C port support a fast 5Gbps data rate, significantly boosting your transfer speeds and improving productivity.
- Fast and Reliable 85W Charging: Offers high-capacity, speedy charging for laptops up to 85W, so you spend less time tethered to an outlet and more time being productive.
- What You Get: Anker USB-C Hub (7-in-1), welcome guide, 18-month warranty, and our friendly customer service.
Which speech providers work, and when do I need two API keys?
saymd documents a bring-your-own-key model. You choose a provider, obtain its key yourself, and pay that provider directly; the project says it does not sell transcription credits. The important distinction is whether the chosen provider also performs Markdown structuring.
| Provider | Documented model | Transcription | Markdown structuring | Keys required |
|---|---|---|---|---|
| Gemini | gemini-3.5-transcribe |
Yes | Yes, according to the project | Gemini key |
| OpenAI | gpt-4o-transcribe |
Yes | Yes, according to the project | OpenAI key |
| Deepgram | nova-3 |
Yes | No; a Gemini or OpenAI key is also needed | Deepgram key plus Gemini or OpenAI key |
| ElevenLabs | scribe_v2 |
Yes | No; a Gemini or OpenAI key is also needed | ElevenLabs key plus Gemini or OpenAI key |
These are project-documented capabilities, not a comparative accuracy or price test. Provider model names and account requirements are volatile; confirm the current model ID and billing terms in the provider’s own console before configuring a production workflow.
Where are keys and audio stored?
The project says API keys stay on your machine, either in ~/.saymd/config.json with file mode 0600 or in environment variables. It also says audio is sent only to the speech-to-text provider you select and that saymd.app does not receive audio, transcripts, or prompt files.
The Tool Desk
Outbyte Driver Updater FREEScan for outdated or missing drivers - takes under a minuteDriver Scan →Outbyte PC Repair FREERepair Windows errors before they cause bigger problemsFix Now →Those are claims from the author and project documentation, not the result of an independent security audit. If your requirements prohibit sending voice data to a third party, do not assume local processing: the documented workflow calls a provider API. Check your organization’s retention, regional-processing, and logging policies before recording confidential material, and avoid placing secrets in spoken requirements.
How long can I record, and what languages are supported?
The documented Free limits are a 60-second default and a 60-second maximum per recording. Pro raises the default to 120 seconds and lists a 10-minute maximum per recording. The project notes that these limits can change, so verify them in the current package documentation when the cap matters to your workflow.
Free is described as supporting more than 85 input languages with automatic detection, and output remains in the language you speak. Cross-language output through an --out option is listed as a Pro capability. “85+” is a product capability claim, not an independently measured language-accuracy result; accents, domain vocabulary, and noisy rooms can still affect the transcript.
Rank #4
- Dual Converters, Infinite Potential：Includes 2× USB C male to USB A female adapters and 2× USB A male to USB C female adapters. Perfect for a wide range of uses—tablets with Bluetooth keyboards, expand USB ports on macbook, and more. Two different converters for all your daily needs
- Next-Level 10Gbps & 3A Charging: No more slow 480Mbps, this usb to usb c adapter has a transfer speed of up to 10Gbps, allowing you to do more transferring in less time. This usb adapter fits both USB A and USB C charger, supporting up to 3A fast charging
- Upgraded Exquisite Craftsmanship: With an aluminum alloy housing and metal connector, the usbc to usb adapter is extremely durable and sturdy. Rigorously tested to withstand more than 10,000 times of plugging and unplugging, ensuring long-lasting performance
- Broad Compatible: The usb c to usb adapter widely supports all USB C/ USB A devices like laptops, tablets, cellphones, car chargers, and phone chargers. Such as compatible with MacBook Pro/Air 2023/2022, Thunderbolt 4/3 Devices,Apple MagSafe Watch 9/8/7/SE/Ultra, iPad Pro 2022/2021, Samsung Galaxy S23/S20/S10, and iPhone 17/16/15 Pro. Plug and play
- Please Note: To reach 10Gbps speed, keep the cable under 3.3 ft. For USB A Male to USB C adapters, try flipping the USB C connector. USB C Male to USB A adapters support bidirectional 10Gbps transfer within 3.3 ft
What is included in Free versus Pro?
Free is the complete MIT-licensed CLI for short recordings. Pro is a separate proprietary package, @saymd/pro, aimed at longer or iterative specification work rather than a switch that unlocks features inside the Free repository.
Recommended Free Tools
| Capability | Free CLI | Pro package |
|---|---|---|
| Core voice-to-Markdown workflow | Yes | Yes |
| Recording allowance | 60-second default and maximum, per project documentation | 120-second default; 10-minute maximum, per project documentation |
| Continue an existing spec with more speech | Not listed | --continue |
| Review for missing requirements or constraints | Not listed | --review |
| Cross-language output | Not listed | --out |
| Project vocabulary | Not listed | .saymd/vocab.txt |
| Price | Free | €39 per year is stated by the author; a monthly option is mentioned without a stated price |
The practical upgrade path is incremental: keep using the MIT CLI, then add Pro if continuation, review, project-specific vocabulary, cross-language output, or longer takes justify the separate package. Confirm the current seller, package availability, and price before purchase because all three can change.
How do the ChatGPT, Codex, and other plugin surfaces work?
The plugin package exposes slash commands that map to common prompt tasks: /saymd, /saymd-feature, /saymd-bug, /saymd-plan, /saymd-continue, /saymd-review, and /saymd-out. Their purpose is to invoke the corresponding capture or refinement flow from an agent interface rather than typing the CLI options manually.
The author reports that saymd was live in the OpenAI ChatGPT/Codex Plugins directory under the descriptor “Voice to Markdown prompts.” The repository documents a Codex manifest and installation paths for Cursor, Claude Code, Grok Build, Antigravity CLI, and Gemini CLI. It also describes an official catalog pull request for Grok as pending, while the author says Claude Code and Cursor publication were under review. Marketplace status is time-sensitive: search the relevant catalog and follow the current installation instructions before promising that a one-click listing exists.
Regardless of the surface, the artifact remains a Markdown file. That makes the workflow less dependent on one agent: you can inspect, version, rename, or hand the file to another tool that supports file references.
What should I do when the generated prompt is incomplete?
Treat the first Markdown file as a draft specification. A short review pass is faster than debugging an agent that acted on an implied requirement.
Best Value
- 5-in-1 Connectivity: Equipped with a 4K HDMI port, a 5 Gbps USB-C data port, two 5 Gbps USB-A ports, and a USB C 100W PD-IN port. Note: The USB C 100W PD-IN port supports only charging and does not support data transfer devices such as headphones or speakers.
- Powerful Pass-Through Charging: Supports up to 85W pass-through charging so you can power up your laptop while you use the hub. Note: Pass-through charging requires a charger (not included). Note: To achieve full power for iPad, we recommend using a 45W wall charger.
- Transfer Files in Seconds: Move files to and from your laptop at speeds of up to 5 Gbps via the USB-C and USB-A data ports. Note: The USB C 5Gbps Data port does not support video output.
- HD Display: Connect to the HDMI port to stream or mirror content to an external monitor in resolutions of up to 4K@30Hz. Note: The USB-C ports do not support video output.
- What You Get: Anker 332 USB-C Hub (5-in-1), welcome guide, our worry-free 18-month warranty, and friendly customer service.
- Check that the objective names the user-visible outcome, not just an implementation idea.
- Add repository paths, framework versions, API contracts, and data shapes that were obvious in your head but absent from the recording.
- Turn vague success language into acceptance criteria, especially with the
featuretemplate. - For a bug, verify that reproduction steps, expected behavior, and actual behavior are all present and ordered.
- Move non-negotiable limits into Constraints so they are not buried in conversational context.
- Ask the agent to read the prompt file before editing and to identify unresolved questions instead of guessing.
If audio is consistently misrecognized, shorten sentences, spell unusual identifiers aloud, and add project terms to the Pro vocabulary file when that feature is available. A clean microphone signal helps, but the project does not require an external microphone; built-in hardware is sufficient if it produces an intelligible recording.
Is saymd a good fit for my coding workflow?
saymd fits teams or individuals who can explain requirements faster by speaking and want a durable, reviewable handoff to an agent. It is especially useful for feature briefs, reproducible bug reports, and implementation plans that would otherwise remain in a long voice note or an unstructured chat message.
It is less suitable when policy forbids sending audio to an external provider, when requirements must be captured in a highly formal schema that the templates do not cover, or when a recording regularly exceeds the edition’s time cap. In those cases, type or edit the Markdown directly, or split a long discussion into several reviewed prompt files.
Quick wins for a faster PC:
Clear out junk files and repair common Windows errorsFree Scan →Fix the driver behind crashes, sound loss and screen glitchesFind Drivers →Frequently Asked Questions
Can I run saymd without paying for a separate subscription?
The project describes the Free CLI as free and MIT licensed, but transcription still uses a provider key that you supply. Any API charges come from the provider account you choose, so “free CLI” does not mean unlimited, cost-free cloud transcription.
Does saymd execute code changes automatically?
No. Its documented output is a Markdown specification. You decide which coding agent reads that file and when to authorize edits, making the prompt reviewable before execution.
Can I keep the generated prompts in Git?
The output is an ordinary Markdown file, so you can place it wherever your project workflow allows and version it like other text. Remove secrets and sensitive speech before committing, and check your repository’s retention policy.
What happens if my recording is longer than the limit?
Use shorter recordings or split the requirement into multiple prompt files. Pro documents a longer allowance, but the exact cap and package availability should be confirmed in the current project documentation before relying on it.
Free tools Windows power users keep installed
One-click scans. No signup required.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
