edgespeak-segment

Installation
SKILL.md

EdgeSpeak Segment

Turn an undifferentiated block of text into natural sentences, on-device. This is a semantic sentence splitter (a small local model), so it works on ASR output that has no punctuation or broken punctuation — where naïve "split on period" fails completely. Under the hood it calls edgespeak-cli segment. When the EdgeSpeak desktop app is running, the CLI talks to its local gateway (OpenAI-compatible, 127.0.0.1:1117) and reuses the warm model (proxy mode); when the app is not running, the CLI launches the bundled on-device engine itself (standalone mode). Standalone is a normal mode, not an error.

Version compatibility. The frontmatter pins this skill's version and the oldest CLI it is written against (minCliVersion). If edgespeak-cli --version reports something older, run edgespeak-cli update (or re-run the installer) before relying on the flags documented here. Same-numbered builds can still differ, so --help is the tiebreaker: a command or flag documented here but missing from the installed --help also means update — don't route around it.

Inputs to confirm

  • Text to segment, preferably as a file path for large input.
  • Desired output: stdout text, .txt, .json, or .srt.
  • Optional sentence-boundary sensitivity threshold.
  • Optional sentence length constraints.

How to do it

  1. Get the text — inline, or (better for long text) a file path.
  2. Check the runtime first:
Installs
6
GitHub Stars
6
First Seen
Jul 28, 2026
edgespeak-segment — lattifai/edgespeak-skills