horizon-speech

Horizon speech input check

This skill uses local audio diagnostics. Horizon has no speech MCP tool. Do not treat dictation as an MCP-controlled capability.

Run this when a user says dictation "types the wrong thing", produces text they never said, or produces nothing.

Read this first

Whisper-family models hallucinate fluent, plausible text when fed silence. Given a digitally silent recording, NB-Whisper will confidently emit something like Esther Smith, forfatter — grammatical, idiomatic, and completely unrelated to the user. The output looks like a model, accent, or dialect problem. It is almost always a capture problem.

So: measure the capture level before touching models, languages, or config. Never conclude "the model is bad at your accent" until step 3 shows real signal.

A user cannot tell these apart from the transcript alone. That is the whole reason this skill exists.

1. Compare configured device against reality

When HORIZON_HOME is set and not empty, Horizon looks for its config only in that folder (config.yaml, then config.yml) and ignores every location below. Otherwise it checks, in order, $HOME/.horizon/, then $XDG_CONFIG_HOME/horizon/, then a relative horizon.yaml/horizon.yml in the working directory. Resolution keys off HOME on every platform — Windows included; USERPROFILE is never consulted, so a native Windows launch without HOME set falls back to the relative path. Confirm which file is actually live before trusting it, or you may inspect a config Horizon never loaded.

Read features.speech from that file:

• input_device: "" means the system default input is used.
• A non-empty name is matched case-insensitively: exact, then substring, then a normalized identity key.

If the configured name matches no present device, Horizon falls back to the system default and only logs a warning. The user never sees it. A config naming a microphone that is no longer plugged in therefore looks like it works. Check the name against the live device list before anything else.