{ "schemaVersion": "1.0", "item": { "slug": "telegram-voice-to-voice-macos", "name": "Telegram Voice To Voice Macos", "source": "tencent", "type": "skill", "category": "通讯协作", "sourceUrl": "https://clawhub.ai/Fiberian1981/telegram-voice-to-voice-macos", "canonicalUrl": "https://clawhub.ai/Fiberian1981/telegram-voice-to-voice-macos", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/telegram-voice-to-voice-macos", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=telegram-voice-to-voice-macos", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "README.md", "SKILL.md", "scripts/transcribe_telegram_ogg.sh", "scripts/tts_telegram_voice.sh" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "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." ], "prompts": [ { "label": "New install", "body": "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." }, { "label": "Upgrade existing", "body": "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." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-30T16:55:25.780Z", "expiresAt": "2026-05-07T16:55:25.780Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/telegram-voice-to-voice-macos" }, "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." ] }, "downloadPageUrl": "https://openagent3.xyz/downloads/telegram-voice-to-voice-macos", "agentPageUrl": "https://openagent3.xyz/skills/telegram-voice-to-voice-macos/agent", "manifestUrl": "https://openagent3.xyz/skills/telegram-voice-to-voice-macos/agent.json", "briefUrl": "https://openagent3.xyz/skills/telegram-voice-to-voice-macos/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "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." ], "prompts": [ { "label": "New install", "body": "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." }, { "label": "Upgrade existing", "body": "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." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "Telegram voice-to-voice (macOS Apple Silicon only)", "body": "This is an OpenClaw skill." }, { "title": "Requirements", "body": "macOS on Apple Silicon.\nyap CLI available in PATH (Speech.framework transcription).\n\nProject: https://github.com/finnvoor/yap (by finnvoor)\n\n\nffmpeg available in PATH." }, { "title": "Compatibility note (important)", "body": "This skill is macOS-only (uses say + Speech.framework). The skill registry cannot enforce OS restrictions, so installing/running it on Linux/Windows will result in runtime failures." }, { "title": "Persistent reply mode (voice vs text)", "body": "Store a small per-user preference file in the workspace:\n\nState file: voice_state/telegram.json\nKey: Telegram sender user id (string)\nValues:\n\n\"voice\" (default): reply with a Telegram voice note\n\"text\": reply with a single text message\n\nIf the file does not exist or the sender id is missing: assume \"voice\"." }, { "title": "Toggle commands", "body": "If an inbound text message is exactly:\n\n/audio off → set state to \"text\" and confirm with a short text reply.\n/audio on → set state to \"voice\" and confirm with a short text reply." }, { "title": "Getting the inbound audio (.ogg)", "body": "Telegram voice notes often show up as in message text.\nOpenClaw saves the attachment to disk (typically .ogg) under:\n\n~/.openclaw/media/inbound/\n\nRecommended approach:\n\nIf the inbound message context includes an attachment path, use it.\nOtherwise, take the most recent *.ogg from ~/.openclaw/media/inbound/." }, { "title": "Transcription", "body": "Default locale: macOS system locale.\n\nOptional env:\n\nYAP_LOCALE — override the transcription locale (e.g. it-IT, en-US).\n\nPreferred:\n\nyap transcribe --locale \"${YAP_LOCALE:-}\" \n\nIf YAP_LOCALE is not set, the helper script will use the macOS system locale (from defaults read -g AppleLocale).\n\nIf transcription fails or is empty: ask the user to repeat or send text.\n\nHelper script:\n\nscripts/transcribe_telegram_ogg.sh [path.ogg]" }, { "title": "Mode: voice (default)", "body": "Voice default: SYSTEM (uses the current macOS system voice). You can override by passing a specific voice name to the helper script.\n\nGenerate the reply text.\nConvert reply text to an OGG/Opus voice note using:\n\nscripts/tts_telegram_voice.sh \"\" [SYSTEM|VoiceName]\n\nThe script prints the generated .ogg path to stdout.\n\nSend the .ogg back to Telegram as a voice note (not a generic audio file):\n\nuse the message tool with asVoice: true and media: \noptionally set replyTo to thread the response\n\nNotes:\n\nUse SYSTEM to rely on the current macOS system voice (recommended)." }, { "title": "Mode: text", "body": "Reply with a single text message:\n\nTranscription: <...>\nReply: <...>" } ], "body": "Telegram voice-to-voice (macOS Apple Silicon only)\n\nThis is an OpenClaw skill.\n\nRequirements\nmacOS on Apple Silicon.\nyap CLI available in PATH (Speech.framework transcription).\nProject: https://github.com/finnvoor/yap (by finnvoor)\nffmpeg available in PATH.\nCompatibility note (important)\n\nThis skill is macOS-only (uses say + Speech.framework). The skill registry cannot enforce OS restrictions, so installing/running it on Linux/Windows will result in runtime failures.\n\nPersistent reply mode (voice vs text)\n\nStore a small per-user preference file in the workspace:\n\nState file: voice_state/telegram.json\nKey: Telegram sender user id (string)\nValues:\n\"voice\" (default): reply with a Telegram voice note\n\"text\": reply with a single text message\n\nIf the file does not exist or the sender id is missing: assume \"voice\".\n\nToggle commands\n\nIf an inbound text message is exactly:\n\n/audio off → set state to \"text\" and confirm with a short text reply.\n/audio on → set state to \"voice\" and confirm with a short text reply.\nGetting the inbound audio (.ogg)\n\nTelegram voice notes often show up as in message text. OpenClaw saves the attachment to disk (typically .ogg) under:\n\n~/.openclaw/media/inbound/\n\nRecommended approach:\n\nIf the inbound message context includes an attachment path, use it.\nOtherwise, take the most recent *.ogg from ~/.openclaw/media/inbound/.\nTranscription\n\nDefault locale: macOS system locale.\n\nOptional env:\n\nYAP_LOCALE — override the transcription locale (e.g. it-IT, en-US).\n\nPreferred:\n\nyap transcribe --locale \"${YAP_LOCALE:-}\" \nIf YAP_LOCALE is not set, the helper script will use the macOS system locale (from defaults read -g AppleLocale).\n\nIf transcription fails or is empty: ask the user to repeat or send text.\n\nHelper script:\n\nscripts/transcribe_telegram_ogg.sh [path.ogg]\nReply behavior\nMode: voice (default)\n\nVoice default: SYSTEM (uses the current macOS system voice). You can override by passing a specific voice name to the helper script.\n\nGenerate the reply text.\nConvert reply text to an OGG/Opus voice note using:\nscripts/tts_telegram_voice.sh \"\" [SYSTEM|VoiceName]\n\nThe script prints the generated .ogg path to stdout.\n\nSend the .ogg back to Telegram as a voice note (not a generic audio file):\nuse the message tool with asVoice: true and media: \noptionally set replyTo to thread the response\n\nNotes:\n\nUse SYSTEM to rely on the current macOS system voice (recommended).\nMode: text\n\nReply with a single text message:\n\nTranscription: <...>\nReply: <...>" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/Fiberian1981/telegram-voice-to-voice-macos", "publisherUrl": "https://clawhub.ai/Fiberian1981/telegram-voice-to-voice-macos", "owner": "Fiberian1981", "version": "0.1.3", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/telegram-voice-to-voice-macos", "downloadUrl": "https://openagent3.xyz/downloads/telegram-voice-to-voice-macos", "agentUrl": "https://openagent3.xyz/skills/telegram-voice-to-voice-macos/agent", "manifestUrl": "https://openagent3.xyz/skills/telegram-voice-to-voice-macos/agent.json", "briefUrl": "https://openagent3.xyz/skills/telegram-voice-to-voice-macos/agent.md" } }