← 返回 Skills 市场
ironystock

Autonoannounce

作者 ironystock · GitHub ↗ · v0.2.5 · MIT-0
cross-platform ✓ 安全检测通过
251
总下载
0
收藏
0
当前安装
4
版本数
在 OpenClaw 中安装
/install autonoannounce
功能描述
Build, operate, and troubleshoot Autonoannounce local speaker text-to-speech using the queued pipeline (enqueue to worker to ElevenLabs to playback backend)....
使用说明 (SKILL.md)

Local TTS Queue

Requirements

  • Required credential: ELEVENLABS_API_KEY
  • Recommended env vars: ELEVENLABS_VOICE_ID, ELEVENLABS_MODEL_ID
  • Runtime tools: python3, curl, and one local playback backend (mpv, ffplay, afplay, paplay, or PowerShell sound player)
  • Network destination for synthesis/preflight: https://api.elevenlabs.io

Overview

Use this skill to keep local speech fast, reliable, and policy-compliant by treating enqueue as fire-and-forget and isolating synthesis/playback inside the queue worker.

Quick start workflow

  1. Confirm queue health with scripts/tts-queue-status.sh.
  2. Enqueue speech with scripts/speak-local-queued.sh "text".
  3. If audio does not play, inspect worker logs and runbook steps in references/runbook.md.
  4. For latency tuning, run scripts/benchmark-autonoannounce.sh and compare against SLOs in references/perf-slos.md.

Operating rules

  • Keep the producer path non-blocking: enqueue then return immediately.
  • Keep synthesis/playback in worker-only execution paths.
  • Prefer fewer larger writes to the queue (coalesce bursty traffic when possible).
  • Use policy-safe output lanes: local speaker for protected users; no Discord voice-file fallback.
  • Treat one failed item as isolated: retry with bounds, then dead-letter; do not stall entire queue.

Commands

  • Enqueue: scripts/speak-local-queued.sh "\x3Ctext>"
  • Worker (foreground): scripts/tts-queue-worker.sh
  • Worker daemon: scripts/tts-queue-daemon.sh
  • Status: scripts/tts-queue-status.sh
  • Benchmark harness: scripts/benchmark-autonoannounce.sh
    • Fast foreground benchmark: scripts/benchmark-autonoannounce.sh 5
    • Full diagnostic benchmark: scripts/benchmark-autonoannounce.sh 5 --status both --output full
  • First-run interactive setup: skills/autonoannounce/scripts/setup-first-run.sh (shell wrapper)
  • Cross-platform first-run CLI: skills/autonoannounce/scripts/setup_first_run.py
  • Backend detection (OS-aware): skills/autonoannounce/scripts/backend-detect.sh
  • ElevenLabs capability preflight: skills/autonoannounce/scripts/elevenlabs-preflight.sh (includes short 429 retry/backoff for SFX probe)
  • Earcon library manager (durable categories/cache): skills/autonoannounce/scripts/earcon-library.sh
  • Cross-platform playback runner: skills/autonoannounce/scripts/play-local-audio.sh
  • Playback backend/device probe: skills/autonoannounce/scripts/playback-probe.sh
  • Playback backend startup validator: skills/autonoannounce/scripts/playback-validate.sh
  • Playback confirmation tone: skills/autonoannounce/scripts/playback-test.sh
  • v0.2 smoke tests: skills/autonoannounce/scripts/test-v0.2.sh
  • Race/concurrency stress checks: skills/autonoannounce/scripts/race-stress.sh

References map

  • Runbook: references/runbook.md
  • Config contract: references/config-contract.md
  • Performance SLOs and interpretation: references/perf-slos.md
  • Foreground-latency optimization: references/front-path-optimization.md
  • Durable earcon categories and cache: references/earcon-library.md

Execution checklist

  • Verify prerequisites (ELEVENLABS_API_KEY, ELEVENLABS_VOICE_ID, mpv).
  • Validate queue paths and lock behavior before tuning performance.
  • Measure baseline before making queue/worker changes.
  • Re-run benchmark after each material change.
  • Record final p50/p95 latency and queue-wait deltas in the task summary.
安全使用建议
This skill appears to do what it says: it will send text to api.elevenlabs.io using the ELEVENLABS_API_KEY and store config and generated audio under the local project (.openclaw/, config/, audio/). Before installing, consider: (1) only provide an ElevenLabs API key with the minimal permissions you need and monitor usage (cost/exfiltration risk); (2) run the scripts manually first in a confined environment or container to verify behavior; (3) be aware the skill may generate and store audio files locally (check audio/earcons/ and .openclaw/); (4) optional env vars exist for retry tuning and mock testing — review scripts if you plan to set those. If you need higher assurance, run the included scripts in a disposable VM/container and audit network flows while exercising the skill.
功能分析
Type: OpenClaw Skill Name: autonoannounce Version: 0.2.5 The 'autonoannounce' skill is a comprehensive toolset for managing a local text-to-speech (TTS) queue using the ElevenLabs API. It includes scripts for environment detection (backend-detect.sh), API health checks (elevenlabs-preflight.sh), benchmarking (benchmark-autonoannounce.sh), and automated setup (setup_first_run.py). While the skill possesses broad capabilities such as network access to ElevenLabs and local audio playback execution, these actions are strictly aligned with its stated purpose of providing low-latency, fire-and-forget TTS. The inclusion of concurrency stress tests (race-stress.sh) and detailed performance SLOs indicates a focus on robustness and operational reliability rather than malicious intent.
能力评估
✓ Purpose & Capability
Name/description, required binaries (python3, curl, local players), and the ELEVENLABS_API_KEY align with a local queued TTS pipeline that sends text to ElevenLabs for synthesis and plays audio locally.
ℹ Instruction Scope
Runtime instructions and scripts operate on local config (.openclaw/, config/tts-queue.json, audio/earcons/) and call https://api.elevenlabs.io for synthesis. They do not reference unrelated network endpoints or attempt to read arbitrary system secrets. Note: several optional/test env vars are referenced by scripts (SFX_MAX_RETRIES, SFX_BASE_DELAY_MS, SFX_MAX_DELAY_MS, ELEVENLABS_PREFLIGHT_MOCK, ELEVENLABS_PREFLIGHT_MOCK_SFX_CODES) but these are for retry tuning and mock testing and are not declared in requires.env.
✓ Install Mechanism
No install spec (instruction-only packaging) — code files are provided but nothing is automatically downloaded from external untrusted URLs. Running the skill will execute local scripts; there is no hidden installer that pulls external archives.
✓ Credentials
Only ELEVENLABS_API_KEY is required (with optional ELEVENLABS_VOICE_ID and ELEVENLABS_MODEL_ID). This is proportionate for a skill that performs remote TTS. The scripts do send text to ElevenLabs; users should ensure the API key has appropriate scope and be aware of billing/privacy implications.
✓ Persistence & Privilege
always is false and the skill does not request system-wide privileges. It writes its own config and audio files under the project (.openclaw/, config/, audio/) which is expected behavior for local runtime state.
如何使用
  1. 确保已安装 OpenClaw（本地或 Docker 部署）
  2. 在对话框中输入安装命令：/install autonoannounce
  3. 安装完成后，直接呼叫该 Skill 的名称或使用 /autonoannounce 触发
  4. 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v0.2.5
- Added a metadata field to SKILL.md describing required environment variables, binaries, and homepage for the skill. - No changes made to functional documentation or command usage. - This update improves discoverability and configuration clarity for integrators and automation tools.
v0.2.4
- Adds details on local runtime state files and directories now written during TTS operation (config/tts-queue.json, .openclaw/*, audio/earcons/*). - Clarifies use of https://api.elevenlabs.io for synthesis and preflight calls in the skill description.
v0.2.2
- Added explicit credential and runtime requirements, including support for optional ELEVENLABS_VOICE_ID and ELEVENLABS_MODEL_ID. - Documented required/preferred environment variables and compatible playback backends. - Clarified network dependency on ElevenLabs API for TTS synthesis. - Updated documentation (SKILL.md, runbook, config contract, perf SLOs) for improved setup clarity and troubleshooting. - No major functional changes to pipeline behavior; this update focuses on clearer documentation and usage guidance.
v0.2.1
autonoannounce v0.2.1 - Updated SKILL.md with clearer overview, quick start, and operating rules. - Detailed command references and workflows for queue health, speech enqueue, benchmarking, and troubleshooting. - Expanded operating guidance for policy, performance, and local-compliance. - Added comprehensive references and execution checklist for setup, validation, and performance measurement.
元数据
Slug autonoannounce
版本 0.2.5
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 4
常见问题

Autonoannounce 是什么？

Build, operate, and troubleshoot Autonoannounce local speaker text-to-speech using the queued pipeline (enqueue to worker to ElevenLabs to playback backend).... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 251 次。

如何安装 Autonoannounce？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install autonoannounce」即可一键安装，无需额外配置。

Autonoannounce 是免费的吗？

是的，Autonoannounce 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。

Autonoannounce 支持哪些平台？

Autonoannounce 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 Autonoannounce？

由 ironystock（@ironystock）开发并维护，当前版本 v0.2.5。

推荐 Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191115 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 留言讨论