edgespeak-segment
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
- Get the text — inline, or (better for long text) a file path.
- Check the runtime first: