Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.rime.ai/llms.txt

Use this file to discover all available pages before exploring further.

Rime expands addresses, URLs, and email addresses into their spoken form automatically. Schemes, www. prefixes, paths, hyphens in domains, and common TLDs are all handled.
For a tour of text normalization across all categories, see Text normalization. For specific patterns Rime doesn’t expand cleanly, see Pre-normalizing text.

Addresses

Rime typically pronounces state name abbreviations correctly in the context of an address, but writing out the full state name (e.g., “Massachusetts” instead of “MA”) gives more consistent results. Common street abbreviations like Rd. and St. are pronounced correctly.
FormatExampleReads as
Full street + state name529 Main Street, Boston, Massachusetts 02129five twenty-nine main street, boston, massachusetts, zero two one two nine
Abbreviated street + abbreviated state529 Main St., Boston, MA 02129five twenty-nine main street, boston, massachusetts, zero two one two nine
Mixed529 Main St, Boston, MA 02129five twenty-nine main street, boston, massachusetts, zero two one two nine

URLs

Schemes, www. prefixes, paths, and hyphens in domains are handled. Common TLDs (.com, .org, .io, .ai, etc.) are read letter-by-letter.
FormatExampleReads as
Bare www. URLwww.example.comdouble-u double-u double-u dot example dot com
HTTPS URLhttps://app.rime.aih t t p s colon slash slash app dot rime dot a i
URL with pathwww.shop.com/archivewww dot shop dot com slash archive
URL with hyphenated domainhttps://worldprime.io/aboutHTTPS world prime dot i o slash about

Emails

FormatExampleReads as
Standard emailname@example.comname at example dot com
Email with digitscloud799@icloud.comcloud seven nine nine at i cloud dot com
Emails are handled by Rime’s custom segmentation model. It breaks up compound words and handles punctuation and most top-level domains. If you hear something off, let us know.

Known gaps

Internationalized domain names (non-ASCII characters in URLs) aren’t supported. For the full list of normalization gaps and how to handle them, see Pre-normalizing text.