# Send VoiceClaw to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - Download the package from Yavira. - Extract it into a folder your agent can access. - Paste one of the prompts below and point your agent at the extracted folder. ## Suggested prompts ### New install ```text I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete. ``` ### Upgrade existing ```text I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "voiceclaw", "name": "VoiceClaw", "source": "tencent", "type": "skill", "category": "通讯协作", "sourceUrl": "https://clawhub.ai/Asif2BD/voiceclaw", "canonicalUrl": "https://clawhub.ai/Asif2BD/voiceclaw", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/voiceclaw", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=voiceclaw", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "README.md", "LICENSE", "SECURITY.md", ".clawhubsafe", "SKILL.md", "scripts/transcribe.sh" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "voiceclaw", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-01T17:41:14.558Z", "expiresAt": "2026-05-08T17:41:14.558Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=voiceclaw", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=voiceclaw", "contentDisposition": "attachment; filename=\"voiceclaw-1.0.6.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "voiceclaw" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/voiceclaw" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/voiceclaw", "downloadUrl": "https://openagent3.xyz/downloads/voiceclaw", "agentUrl": "https://openagent3.xyz/skills/voiceclaw/agent", "manifestUrl": "https://openagent3.xyz/skills/voiceclaw/agent.json", "briefUrl": "https://openagent3.xyz/skills/voiceclaw/agent.md" } } ``` ## Documentation ### VoiceClaw Local-only voice I/O for OpenClaw agents. STT: transcribe.sh — converts audio to text via local Whisper binary TTS: speak.sh — converts text to speech via local Piper binary Network calls: none — both scripts run fully offline No cloud APIs, no API keys required ### Prerequisites The following must be installed on the system before using this skill: RequirementPurposewhisper binarySpeech-to-text inferenceggml-base.en.bin model fileWhisper STT modelpiper binaryText-to-speech synthesis*.onnx voice model filesPiper TTS voicesffmpegAudio format conversion See README.md for installation and setup instructions. ### Environment Variables VariableDefaultPurposeWHISPER_BINauto-detected via whichPath to whisper binaryWHISPER_MODEL~/.cache/whisper/ggml-base.en.binPath to Whisper model filePIPER_BINauto-detected via whichPath to piper binaryVOICECLAW_VOICES_DIR~/.local/share/piper/voicesDirectory containing .onnx voice model files ### Verify Setup which whisper && echo "STT binary: OK" which piper && echo "TTS binary: OK" which ffmpeg && echo "ffmpeg: OK" ls "${WHISPER_MODEL:-$HOME/.cache/whisper/ggml-base.en.bin}" && echo "STT model: OK" ls "${VOICECLAW_VOICES_DIR:-$HOME/.local/share/piper/voices}"/*.onnx 2>/dev/null | head -1 && echo "TTS voices: OK" ### Inbound Voice: Transcribe # Transcribe audio → text (supports ogg, mp3, m4a, wav, flac) TRANSCRIPT=$(bash scripts/transcribe.sh /path/to/audio.ogg) Override model path: WHISPER_MODEL=/path/to/ggml-base.en.bin bash scripts/transcribe.sh audio.ogg ### Outbound Voice: Speak # Step 1: Generate WAV (local Piper — no network) WAV=$(bash scripts/speak.sh "Your response here." /tmp/reply.wav en_US-lessac-medium) # Step 2: Convert to OGG Opus (Telegram voice requirement) ffmpeg -i "$WAV" -c:a libopus -b:a 32k /tmp/reply.ogg -y -loglevel error # Step 3: Send via message tool (filePath=/tmp/reply.ogg) Override voice directory: VOICECLAW_VOICES_DIR=/path/to/voices bash scripts/speak.sh "Hello." /tmp/reply.wav ### Available Voices VoiceStyleen_US-lessac-mediumNeutral American (default)en_US-amy-mediumWarm American femaleen_US-joe-mediumAmerican maleen_US-kusal-mediumExpressive American maleen_US-danny-lowDeep American male (fast)en_GB-alba-mediumBritish femaleen_GB-northern_english_male-mediumNorthern British male ### Agent Behavior Rules Voice in → Voice + Text out. Always respond with both a voice reply and a text reply when a voice message is received. Include the transcript. Show "🎙️ I heard: [transcript]" at the top of every text reply to a voice message. Keep voice responses concise. Piper TTS works best under ~200 words — summarize for audio, include full detail in text. Local only. Never use a cloud TTS/STT API. Only the local whisper and piper binaries. Send voice before text. Send the audio file first, then follow with the text reply. ### Full Example # 1. Transcribe inbound voice message TRANSCRIPT=$(bash path/to/voiceclaw/scripts/transcribe.sh /path/to/voice.ogg) # 2. Compose reply and generate audio RESPONSE="Deployment complete. All checks passed." WAV=$(bash path/to/voiceclaw/scripts/speak.sh "$RESPONSE" /tmp/reply_$$.wav) ffmpeg -i "$WAV" -c:a libopus -b:a 32k /tmp/reply_$$.ogg -y -loglevel error # 3. Send voice + text # message(action=send, filePath=/tmp/reply_$$.ogg, ...) # reply: "🎙️ I heard: $TRANSCRIPT\\n\\n$RESPONSE" ### Troubleshooting IssueFixwhisper: command not foundEnsure whisper binary is installed and in PATHWhisper model not foundSet WHISPER_MODEL=/path/to/ggml-base.en.binpiper: command not foundEnsure piper binary is installed and in PATHVoice model missingSet VOICECLAW_VOICES_DIR=/path/to/voices/OGG won't play on TelegramEnsure -c:a libopus flag in ffmpeg command ## Trust - Source: tencent - Verification: Indexed source record - Publisher: Asif2BD - Version: 1.0.6 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-05-01T17:41:14.558Z - Expires at: 2026-05-08T17:41:14.558Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/voiceclaw) - [Send to Agent page](https://openagent3.xyz/skills/voiceclaw/agent) - [JSON manifest](https://openagent3.xyz/skills/voiceclaw/agent.json) - [Markdown brief](https://openagent3.xyz/skills/voiceclaw/agent.md) - [Download page](https://openagent3.xyz/downloads/voiceclaw)