Skip to main content

Ready-to-use VOICE.md copy profiles and optional benchmarks for AI-generated copy.

Project description

site2voice

Drop-in VOICE.md copy profiles. Pick a public writing pattern, save one file, and your agent writes less generic copy.

site2voice is not a visual design-system library and not a brand-cloning tool. It turns public copy into a compact, reference-only writing contract: sentence rhythm, heading shape, CTA verb shape, claim boundaries, and benchmark gates.

No install. No JSON. No generation step.

Not official. Not affiliated. Not permission to impersonate a brand.

Featured Profiles

Profile Tone Best for
Apple premium, minimal product launches
Anthropic measured, institutional AI safety and product pages
EYESMAG concise, culture-led Korean fashion and lifestyle copy
Figma collaborative, creative design-tool pages
GitHub developer-first platform and ecosystem copy
Highsnobiety editorial, commerce-aware culture and fashion launches
Hypebeast trend-led streetwear and culture blurbs
Linear precise, product-team SaaS positioning
Monocle polished, global city, design, and affairs copy
Notion simple, workspace productivity pages
OpenAI research-to-product AI product pages
Shopify merchant-growth commerce pages
Stripe calm, technical fintech and SaaS copy
Vercel performance-led developer platform pages
Wallpaper design-editorial architecture and interiors copy

The full collection now includes 33 reference-only profiles, including popular web products such as Canva, LinkedIn, Netflix, TikTok, WhatsApp, Zoom, and PayPal. See the full collection and the popular-sites analysis.

Use

Download one copy profile as VOICE.md:

curl -L https://raw.githubusercontent.com/SihyeonJeon/site2voice/main/voices/stripe.md -o VOICE.md

Tell Claude Code, Codex, Cursor, or Copilot:

Use @VOICE.md as a copy contract for headings, CTA shape, paragraph rhythm, and UI microcopy.

Each file is a plain Markdown writing brief with sentence rhythm, heading shape, CTA verbs, content boundaries, claim boundaries, and a benchmark target. The public profiles remove source nouns, raw CTAs, navigation labels, paragraph samples, logos, screenshots, and brand assets.

Reference names identify the public page used for measurement. They do not imply sponsorship, endorsement, affiliation, or permission to reuse protected brand identity. See Brand Usage.

Not DESIGN.md

DESIGN.md describes visual identity: colors, typography, spacing, components, layout, and responsive behavior. VOICE.md describes writing behavior: rhythm, CTA shape, information order, claim safety, and copy-safety gates.

Read the full comparison in DESIGN.md vs VOICE.md and the dated competitive review.

Before / After

Same LedgerFlow prompt, scored against Stripe:

Candidate Result Overall Variety CTA Copy safety
Without VOICE.md FAIL 63.8 40.5 25.0 100.0
With VOICE.md PASS 91.1 45.8 100.0 96.2

See the full comparison.

Optional CLI

Generate a new copy profile from any public URL:

pipx install site2voice
site2voice init https://example.com

Validate generated copy:

site2voice bench https://example.com draft.md --strict

Need voice.json or an agent prompt too? Use the full context packs.

Status

PyPI CI License: MIT

Develop

python3 -m pip install -e .
make test
make bench-ci

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

site2voice-0.5.3.tar.gz (69.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

site2voice-0.5.3-py3-none-any.whl (16.8 kB view details)

Uploaded Python 3

File details

Details for the file site2voice-0.5.3.tar.gz.

File metadata

  • Download URL: site2voice-0.5.3.tar.gz
  • Upload date:
  • Size: 69.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for site2voice-0.5.3.tar.gz
Algorithm Hash digest
SHA256 0ce7436003d962ca4b143bdb5e0a354291c6edca95a3a38975bcb0e5a40ef7fc
MD5 042ee6d13430e23462e711458c0c4253
BLAKE2b-256 5881f3b2449ebd1197017fffce3d3b326e49f7081d2236e8ab9cb1d84bed3e5a

See more details on using hashes here.

Provenance

The following attestation bundles were made for site2voice-0.5.3.tar.gz:

Publisher: publish.yml on SihyeonJeon/site2voice

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file site2voice-0.5.3-py3-none-any.whl.

File metadata

  • Download URL: site2voice-0.5.3-py3-none-any.whl
  • Upload date:
  • Size: 16.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for site2voice-0.5.3-py3-none-any.whl
Algorithm Hash digest
SHA256 3ad74503ea84ff3c189556a603b7ed7ceb5799406d56f8a64186918b0e9a5916
MD5 8b5b02f81a081cdc1a28323e5b5132e1
BLAKE2b-256 92f647eca242220aca50782fcdb2618404a181ba80fbb800f6cc98c86b9330d0

See more details on using hashes here.

Provenance

The following attestation bundles were made for site2voice-0.5.3-py3-none-any.whl:

Publisher: publish.yml on SihyeonJeon/site2voice

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page