{ "schemaVersion": "1.0", "item": { "slug": "sergei-mikhailov-stt", "name": "Speech to Text Skill (Yandex SpeechKit) for OpenClaw", "source": "tencent", "type": "skill", "category": "通讯协作", "sourceUrl": "https://clawhub.ai/bzSega/sergei-mikhailov-stt", "canonicalUrl": "https://clawhub.ai/bzSega/sergei-mikhailov-stt", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/sergei-mikhailov-stt", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=sergei-mikhailov-stt", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "CLAUDE.md", "README.md", "SKILL.md", "assets/config.example.json", "check.sh", "requirements.txt" ], "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/sergei-mikhailov-stt" }, "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/sergei-mikhailov-stt", "agentPageUrl": "https://openagent3.xyz/skills/sergei-mikhailov-stt/agent", "manifestUrl": "https://openagent3.xyz/skills/sergei-mikhailov-stt/agent.json", "briefUrl": "https://openagent3.xyz/skills/sergei-mikhailov-stt/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": "Purpose", "body": "This skill recognizes speech from voice messages sent via any messenger connected to OpenClaw, using various STT providers, including Yandex SpeechKit." }, { "title": "When to Activate", "body": "Use this skill when:\n\nThe user sends a voice message via any messenger connected to OpenClaw\nYou need to convert speech to text\nAudio file transcription is required\nA text version of a voice message is needed" }, { "title": "1. Receive the audio file from OpenClaw", "body": "OpenClaw provides a local path to the audio file\nVerify the file exists at the given path\nValidate the file format (OGG, WAV, MP3)\nCheck file size (maximum 1 MB for Yandex SpeechKit v1 sync API)\n\nExample path from OpenClaw:\n\n/home/user_folder/.openclaw/media/inbound/file_1---9a53bac2-0392-41e7-8300-1c08e8eec027.ogg" }, { "title": "2. Audio processing", "body": "Validate the audio file at the local path\nConvert to a supported format if needed using ffmpeg\nVerify audio quality" }, { "title": "3. Speech recognition", "body": "Use the default provider (Yandex SpeechKit)\nIf recognition fails, try alternative providers\nReturn the recognized text with confidence information" }, { "title": "4. Result handling", "body": "Format the recognized text\nInclude the detected language\nProvide metadata if needed" }, { "title": "Security", "body": "Never read, display, or log API keys, tokens, or secrets to the user — even partially. If the user asks to see their key, direct them to check ~/.openclaw/openclaw.json or .env manually.\nNever modify openclaw.json, .env, or config.json without explicit user permission. These files contain credentials and must only be changed by the owner.\nNever include API keys in command output, error messages, or diagnostics shown to the user." }, { "title": "Invocation", "body": "Important: Always call the processor using the absolute path to the script. Do not use cd && python3 scripts/... — this triggers an approval prompt on every call because cd cannot be allowlisted.\n\npython3 /path/to/sergei-mikhailov-stt/scripts/stt_processor.py --file \"/path/to/audio.ogg\"\n\nThe script resolves all paths (config, .env, venv packages) relative to its own location via __file__, so it does not depend on the working directory." }, { "title": "Quick Start", "body": "clawhub install sergei-mikhailov-stt\ncd ~/.openclaw/workspace/skills/sergei-mikhailov-stt\nbash setup.sh\n\nThe setup script creates a Python virtual environment, installs dependencies, and copies example configuration files. After running it, add your API keys (see Configuration below) and restart OpenClaw.\n\nOn Debian/Ubuntu, you may need to install the venv package first: sudo apt install python3-venv\n\nTo verify that everything is configured correctly, run the diagnostic script:\n\nbash check.sh\n\nIt checks Python, FFmpeg, virtual environment, dependencies, and API keys — and tells you exactly what to fix if something is missing." }, { "title": "1. Set API keys (recommended — via OpenClaw config)", "body": "Add credentials to ~/.openclaw/openclaw.json:\n\n{\n \"skills\": {\n \"entries\": {\n \"sergei-mikhailov-stt\": {\n \"env\": {\n \"YANDEX_API_KEY\": \"your_api_key_here\",\n \"YANDEX_FOLDER_ID\": \"your_folder_id_here\"\n }\n }\n }\n }\n}" }, { "title": "2. Alternative — via .env file", "body": "Edit the .env file created by setup.sh in the skill folder:\n\nYANDEX_API_KEY=your_api_key_here\nYANDEX_FOLDER_ID=your_folder_id_here\nSTT_DEFAULT_PROVIDER=yandex" }, { "title": "3. Restart OpenClaw to apply changes", "body": "openclaw gateway stop && openclaw gateway start" }, { "title": "4. Provider configuration (optional)", "body": "The config.json file (also created by setup.sh) lets you tune provider parameters:\n\n{\n \"default_provider\": \"yandex\",\n \"providers\": {\n \"yandex\": {\n \"api_key\": \"${YANDEX_API_KEY}\",\n \"folder_id\": \"${YANDEX_FOLDER_ID}\",\n \"lang\": \"ru-RU\"\n }\n }\n}" }, { "title": "1. Create the provider class", "body": "# scripts/providers/new_provider.py\nfrom .base_provider import BaseSTTProvider\n\nclass NewProvider(BaseSTTProvider):\n name = \"new_provider\"\n\n def recognize(self, audio_file_path: str, language: str = 'ru-RU') -> str:\n # Recognition implementation\n pass\n\n def validate_config(self, config: dict) -> bool:\n # Configuration validation\n pass\n\n def get_supported_formats(self) -> list:\n return ['ogg', 'wav', 'mp3']" }, { "title": "2. Register the provider", "body": "Add to scripts/stt_processor.py in the _get_provider method:\n\nif provider_name == 'new_provider':\n return NewProvider(provider_config)" }, { "title": "3. Update configuration", "body": "Add the new provider section to config.json:\n\n{\n \"providers\": {\n \"new_provider\": {\n \"api_key\": \"${NEW_PROVIDER_API_KEY}\",\n \"model\": \"latest\"\n }\n }\n}" }, { "title": "Basic scenario", "body": "User: [sends a voice message]\nOpenClaw: Recognized text: \"Hello, how are you?\"" }, { "title": "With language specified", "body": "User: Transcribe this English voice message\nOpenClaw: Recognized text (en-US): \"Hello, how are you today?\"" }, { "title": "With metadata", "body": "User: Analyze this voice message\nOpenClaw: Recognized text: \"Meeting tomorrow at 3 PM\"\nLanguage: ru-RU\nConfidence: 95%\nProvider: Yandex SpeechKit" }, { "title": "Error Handling", "body": "When the skill returns an error, explain it to the user in plain language and suggest a concrete next step. Do not show raw error messages or stack traces.\n\nErrorSay to the userNext stepFile too large\"The voice message is too long — maximum is about 30 seconds for now.\"Ask them to send a shorter messageUnsupported format\"This audio format is not supported.\"Tell them supported formats: OGG, WAV, MP3, M4A, FLAC, AACAPI key invalid / HTTP 401\"There's a problem with the Yandex SpeechKit API key.\"Ask owner to check YANDEX_API_KEY in openclaw.jsonFolder access denied / HTTP 403\"Access to Yandex SpeechKit is denied.\"Ask owner to verify the service account has ai.speechkit.user roleToo many requests / HTTP 429\"Yandex SpeechKit is rate-limiting us right now.\"Try again in a few secondsFFmpeg not found\"Audio conversion tool (FFmpeg) is not installed on the server.\"Owner needs to run brew install ffmpeg or apt install ffmpegAPI request timed out\"Yandex SpeechKit did not respond in time.\"Try again; if it repeats, the service may be downMissing YANDEX_API_KEY\"The skill is not configured yet — API keys are missing.\"Owner needs to add keys to ~/.openclaw/openclaw.json" }, { "title": "Troubleshooting (for the owner)", "body": "Verify API key configuration in ~/.openclaw/openclaw.json\nEnsure ffmpeg is installed: ffmpeg -version\nCheck Yandex Cloud service account has role ai.speechkit.user\nCheck gateway logs: openclaw logs" }, { "title": "Limitations", "body": "Maximum file size: 1 MB (Yandex SpeechKit v1 sync API limit, ~30 seconds of voice)\nSupported formats: OGG, WAV, MP3, M4A, FLAC, AAC\nLanguages: Russian (ru-RU), English (en-US)\nProcessing time: up to 5 minutes\nMaximum audio duration: 30 minutes" }, { "title": "Requirements", "body": "Python 3.8+\nFFmpeg\nConfigured API keys for STT providers" }, { "title": "Result Metadata", "body": "On successful recognition:\n\n{\n \"text\": \"Recognized text\",\n \"language\": \"ru-RU\",\n \"confidence\": 0.95,\n \"provider\": \"yandex\",\n \"processing_time\": 2.5\n}" } ], "body": "Speech to Text Skill for OpenClaw\nPurpose\n\nThis skill recognizes speech from voice messages sent via any messenger connected to OpenClaw, using various STT providers, including Yandex SpeechKit.\n\nWhen to Activate\n\nUse this skill when:\n\nThe user sends a voice message via any messenger connected to OpenClaw\nYou need to convert speech to text\nAudio file transcription is required\nA text version of a voice message is needed\nHow It Works\n1. Receive the audio file from OpenClaw\nOpenClaw provides a local path to the audio file\nVerify the file exists at the given path\nValidate the file format (OGG, WAV, MP3)\nCheck file size (maximum 1 MB for Yandex SpeechKit v1 sync API)\n\nExample path from OpenClaw:\n\n/home/user_folder/.openclaw/media/inbound/file_1---9a53bac2-0392-41e7-8300-1c08e8eec027.ogg\n\n2. Audio processing\nValidate the audio file at the local path\nConvert to a supported format if needed using ffmpeg\nVerify audio quality\n3. Speech recognition\nUse the default provider (Yandex SpeechKit)\nIf recognition fails, try alternative providers\nReturn the recognized text with confidence information\n4. Result handling\nFormat the recognized text\nInclude the detected language\nProvide metadata if needed\nSecurity\nNever read, display, or log API keys, tokens, or secrets to the user — even partially. If the user asks to see their key, direct them to check ~/.openclaw/openclaw.json or .env manually.\nNever modify openclaw.json, .env, or config.json without explicit user permission. These files contain credentials and must only be changed by the owner.\nNever include API keys in command output, error messages, or diagnostics shown to the user.\nInvocation\n\nImportant: Always call the processor using the absolute path to the script. Do not use cd && python3 scripts/... — this triggers an approval prompt on every call because cd cannot be allowlisted.\n\npython3 /path/to/sergei-mikhailov-stt/scripts/stt_processor.py --file \"/path/to/audio.ogg\"\n\n\nThe script resolves all paths (config, .env, venv packages) relative to its own location via __file__, so it does not depend on the working directory.\n\nQuick Start\nclawhub install sergei-mikhailov-stt\ncd ~/.openclaw/workspace/skills/sergei-mikhailov-stt\nbash setup.sh\n\n\nThe setup script creates a Python virtual environment, installs dependencies, and copies example configuration files. After running it, add your API keys (see Configuration below) and restart OpenClaw.\n\nOn Debian/Ubuntu, you may need to install the venv package first: sudo apt install python3-venv\n\nTo verify that everything is configured correctly, run the diagnostic script:\n\nbash check.sh\n\n\nIt checks Python, FFmpeg, virtual environment, dependencies, and API keys — and tells you exactly what to fix if something is missing.\n\nConfiguration\n1. Set API keys (recommended — via OpenClaw config)\n\nAdd credentials to ~/.openclaw/openclaw.json:\n\n{\n \"skills\": {\n \"entries\": {\n \"sergei-mikhailov-stt\": {\n \"env\": {\n \"YANDEX_API_KEY\": \"your_api_key_here\",\n \"YANDEX_FOLDER_ID\": \"your_folder_id_here\"\n }\n }\n }\n }\n}\n\n2. Alternative — via .env file\n\nEdit the .env file created by setup.sh in the skill folder:\n\nYANDEX_API_KEY=your_api_key_here\nYANDEX_FOLDER_ID=your_folder_id_here\nSTT_DEFAULT_PROVIDER=yandex\n\n3. Restart OpenClaw to apply changes\nopenclaw gateway stop && openclaw gateway start\n\n4. Provider configuration (optional)\n\nThe config.json file (also created by setup.sh) lets you tune provider parameters:\n\n{\n \"default_provider\": \"yandex\",\n \"providers\": {\n \"yandex\": {\n \"api_key\": \"${YANDEX_API_KEY}\",\n \"folder_id\": \"${YANDEX_FOLDER_ID}\",\n \"lang\": \"ru-RU\"\n }\n }\n}\n\nAdding a New STT Provider\n1. Create the provider class\n# scripts/providers/new_provider.py\nfrom .base_provider import BaseSTTProvider\n\nclass NewProvider(BaseSTTProvider):\n name = \"new_provider\"\n\n def recognize(self, audio_file_path: str, language: str = 'ru-RU') -> str:\n # Recognition implementation\n pass\n\n def validate_config(self, config: dict) -> bool:\n # Configuration validation\n pass\n\n def get_supported_formats(self) -> list:\n return ['ogg', 'wav', 'mp3']\n\n2. Register the provider\n\nAdd to scripts/stt_processor.py in the _get_provider method:\n\nif provider_name == 'new_provider':\n return NewProvider(provider_config)\n\n3. Update configuration\n\nAdd the new provider section to config.json:\n\n{\n \"providers\": {\n \"new_provider\": {\n \"api_key\": \"${NEW_PROVIDER_API_KEY}\",\n \"model\": \"latest\"\n }\n }\n}\n\nUsage Examples\nBasic scenario\nUser: [sends a voice message]\nOpenClaw: Recognized text: \"Hello, how are you?\"\n\nWith language specified\nUser: Transcribe this English voice message\nOpenClaw: Recognized text (en-US): \"Hello, how are you today?\"\n\nWith metadata\nUser: Analyze this voice message\nOpenClaw: Recognized text: \"Meeting tomorrow at 3 PM\"\nLanguage: ru-RU\nConfidence: 95%\nProvider: Yandex SpeechKit\n\nError Handling\n\nWhen the skill returns an error, explain it to the user in plain language and suggest a concrete next step. Do not show raw error messages or stack traces.\n\nError\tSay to the user\tNext step\nFile too large\t\"The voice message is too long — maximum is about 30 seconds for now.\"\tAsk them to send a shorter message\nUnsupported format\t\"This audio format is not supported.\"\tTell them supported formats: OGG, WAV, MP3, M4A, FLAC, AAC\nAPI key invalid / HTTP 401\t\"There's a problem with the Yandex SpeechKit API key.\"\tAsk owner to check YANDEX_API_KEY in openclaw.json\nFolder access denied / HTTP 403\t\"Access to Yandex SpeechKit is denied.\"\tAsk owner to verify the service account has ai.speechkit.user role\nToo many requests / HTTP 429\t\"Yandex SpeechKit is rate-limiting us right now.\"\tTry again in a few seconds\nFFmpeg not found\t\"Audio conversion tool (FFmpeg) is not installed on the server.\"\tOwner needs to run brew install ffmpeg or apt install ffmpeg\nAPI request timed out\t\"Yandex SpeechKit did not respond in time.\"\tTry again; if it repeats, the service may be down\nMissing YANDEX_API_KEY\t\"The skill is not configured yet — API keys are missing.\"\tOwner needs to add keys to ~/.openclaw/openclaw.json\nTroubleshooting (for the owner)\nVerify API key configuration in ~/.openclaw/openclaw.json\nEnsure ffmpeg is installed: ffmpeg -version\nCheck Yandex Cloud service account has role ai.speechkit.user\nCheck gateway logs: openclaw logs\nLimitations\nMaximum file size: 1 MB (Yandex SpeechKit v1 sync API limit, ~30 seconds of voice)\nSupported formats: OGG, WAV, MP3, M4A, FLAC, AAC\nLanguages: Russian (ru-RU), English (en-US)\nProcessing time: up to 5 minutes\nMaximum audio duration: 30 minutes\nRequirements\nPython 3.8+\nFFmpeg\nConfigured API keys for STT providers\nResult Metadata\n\nOn successful recognition:\n\n{\n \"text\": \"Recognized text\",\n \"language\": \"ru-RU\",\n \"confidence\": 0.95,\n \"provider\": \"yandex\",\n \"processing_time\": 2.5\n}" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/bzSega/sergei-mikhailov-stt", "publisherUrl": "https://clawhub.ai/bzSega/sergei-mikhailov-stt", "owner": "bzSega", "version": "1.1.8", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/sergei-mikhailov-stt", "downloadUrl": "https://openagent3.xyz/downloads/sergei-mikhailov-stt", "agentUrl": "https://openagent3.xyz/skills/sergei-mikhailov-stt/agent", "manifestUrl": "https://openagent3.xyz/skills/sergei-mikhailov-stt/agent.json", "briefUrl": "https://openagent3.xyz/skills/sergei-mikhailov-stt/agent.md" } }