C Voice
技能 活跃Convert speech to text using `sag` (ElevenLabs STT) and synthesize speech using `say` (macOS built-in TTS). Enables voice input transcription and audio output.
To integrate voice input and output capabilities into Claude Code, allowing for spoken audio transcription and synthesized speech responses.
功能
- Speech-to-text transcription via sag (ElevenLabs STT)
- Text-to-speech synthesis via say (macOS built-in TTS)
- Recording audio from microphone
- Processing various audio file formats (MP3, WAV, M4A, FLAC)
使用场景
- Transcribing spoken commands or dictation into text
- Reading Claude's responses or summaries aloud
- Capturing audio for analysis or documentation
非目标
- Real-time voice chat
- Cross-platform speech synthesis (beyond macOS for `say`)
Documentation
- warning:Configuration & parameter referenceWhile tools are documented, the explicit requirement for an ElevenLabs API key and its configuration is mentioned in 'Notes' and not as a formal parameter or prerequisite.
Maintenance
- warning:Commit recencyThe last commit was over 2 months ago (March 6, 2026), indicating potential lack of recent maintenance.
Security
- warning:Secret ManagementThe skill requires an ElevenLabs API key, which is mentioned as an environment variable in the notes but not explicitly detailed in the setup or prerequisites regarding secure handling.
Trust
- warning:Issues AttentionThere is 1 open issue from the last 90 days and 0 closed issues, indicating slow or no maintainer response to recent issues.
Versioning
- warning:Release ManagementThe extension uses the `main` branch for installation and does not declare a specific version in its frontmatter or manifests, making version pinning difficult.
Compliance
- info:GDPRThe skill processes audio and text, which could potentially include personal data if spoken. However, it does not submit this data to a third party without explicit use of the ElevenLabs API.
Portability
- warning:Runtime stabilityThe skill explicitly states `say` is macOS built-in, implying it may not function on other operating systems. The `sag` tool's cross-platform compatibility is not detailed.
Install
- warning:Installation instructionThe SKILL.md details how to use the tools but assumes the user will install `sag` and have macOS for `say`. It mentions an ElevenLabs API key requirement but lacks explicit installation and setup instructions for `sag` or API key configuration verification.
Execution
- warning:Pinned dependenciesThe skill relies on external CLIs (`sag`) and macOS built-ins (`say`). While `sag` might be installed via a package manager, there's no explicit pinning or lockfile mentioned for it, and no side-effect headers are applicable to these non-script tools.
安装
npx skills add daxaur/openpaw通过 npx 运行 Vercel skills CLI(skills.sh)— 需要本地安装 Node.js,以及至少一个兼容 skills 的智能体(Claude Code、Cursor、Codex 等)。前提是仓库遵循 agentskills.io 格式。
质量评分
类似扩展
Google Tts
100Convert documents and text to audio using Google Cloud Text-to-Speech. Use this skill when the user wants to: narrate a document, read aloud text, generate audio from a file, convert text to speech, create a recording of documentation or analysis, create a podcast from a document, or use Google TTS/text-to-speech. Trigger phrases: "read this aloud", "narrate this", "create a recording", "text to speech", "TTS", "convert to audio", "audio from document", "listen to this", "generate audio", "google tts", "create a podcast".
Speech Generation Skill
100Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation via the OpenAI Audio API; run the bundled CLI (`scripts/text_to_speech.py`) with built-in voices and require `OPENAI_API_KEY` for live calls. Custom voice creation is out of scope.
Tts
96当用户想要将文本转换为语音、从文本生成音频或制作配音时，请使用此技能。触发词包括：提及 'TTS'、'text to speech'、'speak'、'say'、'voice'、'read aloud'、'audio narration'、'voiceover'、'dubbing'，或要求将书面内容转换为口头音频。在将 EPUB/PDF/SRT/文章转换为音频、从参考音频克隆声音、控制语音中的情感或语速、将语音与字幕时间线对齐或生成每个片段的语音映射音频时，也请使用。
Characteristic Voice
95每当用户希望语音听起来更具人情味、伙伴感或情感表现力时，请使用此技能。触发词包括：任何提及“说得像”、“像...一样说话”、“听起来像”、“伙伴声音”、“安慰我”、“让我开心”、“听起来更像人”、“晚安语音”、“早安语音”，或要求为生成的语音添加填充词、情感或个性。当用户希望模仿特定角色的声音、应用说话风格预设（晚安、早安、安慰、庆祝、聊天）、调整语气等情感参数（如温暖或温柔），或使文本转语音输出听起来像真人说话时，也请使用此技能。如果用户要求“语音消息”、“伙伴音频”、“角色声音”，或者想要带有叹息、笑声、犹豫或真正温暖的声音，请使用此技能。请勿用于没有个性的纯文本转语音、音乐生成、音效或与表情语音无关的常规编码任务。
Sherpa Onnx Tts
99Local text-to-speech via sherpa-onnx (offline, no cloud)
Elevenlabs Tts
99ElevenLabs text-to-speech with 22+ premium voices, multilingual support, and voice tuning via inference.sh CLI. Models: eleven_multilingual_v2 (highest quality), eleven_turbo_v2_5 (low latency), eleven_flash_v2_5 (ultra-fast). Capabilities: text-to-speech, voice selection, stability/style control, 32 languages. Use for: voiceovers, audiobooks, video narration, podcasts, accessibility, IVR. Triggers: elevenlabs, eleven labs, elevenlabs tts, premium tts, professional voice, ai voice, high quality tts, multilingual tts, eleven labs voice, voice generation, natural speech, realistic voice, voice over, speech synthesis