edgespeak-broadcast
Turn text into natural speech fully on-device via EdgeSpeak (Broadcast) — synthesize WAV audio with official named voices, cloned voices, style instructions,…
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-20 00:12
54,036 results
Turn text into natural speech fully on-device via EdgeSpeak (Broadcast) — synthesize WAV audio with official named voices, cloned voices, style instructions,…
Resolve anonymous speaker_N labels in an EdgeSpeak diarized transcript to evidence-backed real names, while preserving the original cluster IDs and leaving…
Split a long run of text into natural sentences on-device via EdgeSpeak using a semantic sentence splitter that works on unpunctuated ASR output, or re-segment…
Translate a timed transcript (EdgeSpeak JSON or SRT) into a target language yourself, keeping a strict 1:1 segment mapping and every timestamp untouched, so…
Run due blueprint maintenance ambiently at autonomy level 2+. Use when a drift nudge reports blueprint tasks due or suggests /blueprint:autopilot.
Obsidian bookmarks: list and add file/folder/heading/saved-search/URL bookmarks. Use when starring or saving notes for quick access.
Bun publish to npm. Use when the user wants to release to npm, preview with --dry-run, publish a scoped package with --access public, or enable --provenance…
ComfyUI routing nodes: typed switches, index switches, broadcast (Anything Everywhere), pipe/context bundles, for/while loops, ExecutionBlocker gates. Use when…
Repo maintenance — incremental repack, gc, branch pruning, stash cleanup, fsck. Use when asked to clean up the repo, run git maintenance/gc, delete merged…
Checks whether the current PR branch is still live and in sync (merged/behind/changes-requested). Use when continuing work on a PR branch before adding commits.
Audit skill tree for overlap, split-pressure, and consolidation candidates. Use when finding confusing skill clusters or surfacing REFERENCE.md extraction…
Refresh the plan to focus on the task at hand. Use when context grew, completed steps muddy it, or you want to clear context and continue in auto mode.
Daily catch-up command that aggregates GitHub and Podio items into an ADHD-friendly Obsidian note
Bidirectional synchronization between GitHub and Podio
Obsidian vault inspection and cross-vault routing via `vault=` prefix. Use when checking vault info (path, size, file count) or targeting a non-active vault.
Obsidian editor workspace: list open tabs, recent files, saved Workspaces. Use when checking what's open, switching layouts, or opening files into tabs.
Fast file finding using fd command-line tool with smart defaults, gitignore awareness, and parallel execution. Use when searching for files by name, extension,…
Classify AI systems under the EU AI Act (Regulation (EU) 2024/1689) and determine compliance obligations. Use when asked to assess AI risk level, check if an…
The English introduction is being prepared.
Use when the user asks how code works, wants to understand architecture, trace execution flows, or explore unfamiliar parts of the codebase. Examples: "How…
Use when the user wants to know what will break if they change something, or needs safety analysis before editing code. Examples: "Is it safe to change X?",…
Task plugin Hook system - 2 official lifecycle hooks (SessionStart, SessionEnd)
Deep bug analysis to break the fix-forget-repeat cycle. Analyzes root cause category, why fixes failed, prevention mechanisms, and captures knowledge into…
Turn your script into an emotional, rhythmic voiceover production. Based on Volcano Engine Doubao TTS 2.0, it supports Chinese, English, and mixed Chinese-English reading: proofread polyphonic characters, surnames, and neutral tones according to context, keep English brand and technical terms in their original form, and use the pronunciation table to set how abbreviations and model numbers are read; arrange timbre, speaking rate, pauses, emotion, and stress for narration and different characters, and connect with the preceding context. First review the reading script with phonetic annotations, then generate WAV audio, SRT as needed…