npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

saymd

v0.1.2

Published

Speak once. Get a prompt file any agent can @.

Downloads

448

Vulnerabilities

Powered byPowered by Snyk
  • 0High
  • 0Medium
  • 0Low

Links

Git

Maintainers

kondasviktorkondasviktor

Keywords

geminiopenaideepgramelevenlabsvoicepromptclicursorclaudespeech-to-textai-agentbyok

Readme

saymd

Speak once. Get a prompt file any agent can @.

Agents execute. saymd delivers a usable spec. Free MIT CLI — bring your own speech-to-text key (BYOK). Works with Cursor · Claude Code · Codex · GitHub Copilot · Gemini CLI · OpenCode. Pro is a separate proprietary package (@saymd/pro) — not in this package.

Free includes

  • Mic or --file audio
  • 85+ languages with auto-detect (output stays in the language you spoke)
  • Exact models: gemini-3.5-transcribe, gpt-4o-transcribe, nova-3, scribe_v2
  • Templates: feature, bug, plan

Start here — Free

npx saymd setup
npx saymd doctor
npx saymd -o .ai/prompt.md --template feature --seconds 30

Speak, press Enter to stop, then @ .ai/prompt.md in Cursor, Claude Code, Codex, Copilot, Gemini CLI, OpenCode, or any agent that can read Markdown.

Default output (no --template): Objective / Context / Instructions / Constraints.

Languages — Free (85+)

Auto-detect across 85+ input languages. Free Markdown is written in the same language you spoke.

saymd --lang hu          # optional hint if auto-detect is wrong
saymd --out en           # Pro: speak one language, write another

Templates — Free

| --template | Headings | |--------------|----------| | feature | Objective, Context, Instructions, Constraints, Acceptance criteria | | bug | Objective, Context, Steps to reproduce, Expected / Actual | | plan | Objective, Context, numbered Steps, Constraints, Open questions | | (none) | Objective, Context, Instructions, Constraints |

saymd --template bug -o .ai/bug.md
saymd --file idea.m4a --template feature -o .ai/feature.md

Audio: mp3, m4a, wav, ogg, opus, flac, webm, aiff, caf, mp4, mov

Recording

Enter to stop. Free: max 60s per take. Pro: default 120s, max 10 min.

BYOK providers (exact models)

You pay the STT provider. Keys in ~/.saymd/config.json (0600) or env — never printed by saymd config.

| --provider | Exact model ID | |--------------|----------------| | gemini (recommended) | gemini-3.5-transcribe | | openai | gpt-4o-transcribe | | deepgram | nova-3 (needs Gemini or OpenAI for structuring) | | elevenlabs | scribe_v2 (needs Gemini or OpenAI for structuring) |

saymd setup
saymd config set provider openai
saymd --provider deepgram --file meeting.wav

Pro

--continue, --review, --out, .saymd/vocab.txt, and longer recordings require saymd.app (€39/yr · €5/mo).

saymd activate <activation-code>
saymd --continue .ai/prompt.md
saymd --review .ai/prompt.md
saymd --out en

Privacy

Audio goes only to the provider you chose, with your key. Privacy

Platforms

macOS + Linux. Windows: WSL or --file only. Node 20+, ffmpeg.

saymd help
saymd --help
saymd doctor

How you can help

Full docs: github.com/kondasviktor/saymd