SKILL.md that
teaches coding agents (Claude Code, Cursor, Codex) how to build a correct,
low-latency KugelAudio integration: when to flush a streaming session, which
latency levers actually matter, and how to write text that sounds right.
Agents load skills from a skills directory such as .claude/skills/; they do
not look inside installed packages. So installing the SDK is not enough: one
command copies the skill where the agent will find it.
Install
./.claude/skills/kugelaudio-tts/. Claude Code picks up a skill
added to a skills directory it already watches without a restart. If the install
created that directory in the first place and the skill doesn’t show up, restart
once so it starts watching it.
Run
npx kugelaudio-skills list (npm), uv run kugelaudio-skills list (uv), or
kugelaudio-skills list (pip) to see what a package version bundles.
What the skill covers
- The four mistakes behind most bad integrations: per-sentence flushing, a new
session per sentence, no pre-connect, unset
language. - The latency levers in priority order, and the chunk-size ordering.
- Writing text for speech: no markdown or emoji,
!and ALL-CAPS as prosody cues,<break>snapping to the trained pause lengths,<spell>, and a drop-in LLM system-prompt block. - Which API surface fits which situation.
- Choosing between the hosted API and an on-premise deployment: a Helm chart your team installs and operates with KugelAudio support, which needs outbound HTTPS to the hosted API.
Commit it or not
Committing.claude/skills/kugelaudio-tts/ pins the guidance for everyone on
the team and for cloud agent sessions, which do not read your machine’s
~/.claude/skills/. Re-run the install command after upgrading the SDK to pick
up a newer version of the skill.
Next steps
Latency
The levers the skill teaches, with measurement guidance
Voice Agent Prompting
Prompt patterns for LLM-driven voice agents