{ "schemaVersion": "1.0", "item": { "slug": "podcast-generation", "name": "Podcast Generation with Microsoft Foundry", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/thegovind/podcast-generation", "canonicalUrl": "https://clawhub.ai/thegovind/podcast-generation", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/podcast-generation", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=podcast-generation", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "references/acceptance-criteria.md", "references/architecture.md", "references/code-examples.md", "scripts/pcm_to_wav.py" ], "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. 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. 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/podcast-generation" }, "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/podcast-generation", "agentPageUrl": "https://openagent3.xyz/skills/podcast-generation/agent", "manifestUrl": "https://openagent3.xyz/skills/podcast-generation/agent.json", "briefUrl": "https://openagent3.xyz/skills/podcast-generation/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. 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. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "Podcast Generation with GPT Realtime Mini", "body": "Generate real audio narratives from text content using Azure OpenAI's Realtime API." }, { "title": "Quick Start", "body": "Configure environment variables for Realtime API\nConnect via WebSocket to Azure OpenAI Realtime endpoint\nSend text prompt, collect PCM audio chunks + transcript\nConvert PCM to WAV format\nReturn base64-encoded audio to frontend for playback" }, { "title": "Environment Configuration", "body": "AZURE_OPENAI_AUDIO_API_KEY=your_realtime_api_key\nAZURE_OPENAI_AUDIO_ENDPOINT=https://your-resource.cognitiveservices.azure.com\nAZURE_OPENAI_AUDIO_DEPLOYMENT=gpt-realtime-mini\n\nNote: Endpoint should NOT include /openai/v1/ - just the base URL." }, { "title": "Backend Audio Generation", "body": "from openai import AsyncOpenAI\nimport base64\n\n# Convert HTTPS endpoint to WebSocket URL\nws_url = endpoint.replace(\"https://\", \"wss://\") + \"/openai/v1\"\n\nclient = AsyncOpenAI(\n websocket_base_url=ws_url,\n api_key=api_key\n)\n\naudio_chunks = []\ntranscript_parts = []\n\nasync with client.realtime.connect(model=\"gpt-realtime-mini\") as conn:\n # Configure for audio-only output\n await conn.session.update(session={\n \"output_modalities\": [\"audio\"],\n \"instructions\": \"You are a narrator. Speak naturally.\"\n })\n \n # Send text to narrate\n await conn.conversation.item.create(item={\n \"type\": \"message\",\n \"role\": \"user\",\n \"content\": [{\"type\": \"input_text\", \"text\": prompt}]\n })\n \n await conn.response.create()\n \n # Collect streaming events\n async for event in conn:\n if event.type == \"response.output_audio.delta\":\n audio_chunks.append(base64.b64decode(event.delta))\n elif event.type == \"response.output_audio_transcript.delta\":\n transcript_parts.append(event.delta)\n elif event.type == \"response.done\":\n break\n\n# Convert PCM to WAV (see scripts/pcm_to_wav.py)\npcm_audio = b''.join(audio_chunks)\nwav_audio = pcm_to_wav(pcm_audio, sample_rate=24000)" }, { "title": "Frontend Audio Playback", "body": "// Convert base64 WAV to playable blob\nconst base64ToBlob = (base64, mimeType) => {\n const bytes = atob(base64);\n const arr = new Uint8Array(bytes.length);\n for (let i = 0; i < bytes.length; i++) arr[i] = bytes.charCodeAt(i);\n return new Blob([arr], { type: mimeType });\n};\n\nconst audioBlob = base64ToBlob(response.audio_data, 'audio/wav');\nconst audioUrl = URL.createObjectURL(audioBlob);\nnew Audio(audioUrl).play();" }, { "title": "Voice Options", "body": "VoiceCharacteralloyNeutralechoWarmfableExpressiveonyxDeepnovaFriendlyshimmerClear" }, { "title": "Realtime API Events", "body": "response.output_audio.delta - Base64 audio chunk\nresponse.output_audio_transcript.delta - Transcript text\nresponse.done - Generation complete\nerror - Handle with event.error.message" }, { "title": "Audio Format", "body": "Input: Text prompt\nOutput: PCM audio (24kHz, 16-bit, mono)\nStorage: Base64-encoded WAV" }, { "title": "References", "body": "Full architecture: See references/architecture.md for complete stack design\nCode examples: See references/code-examples.md for production patterns\nPCM conversion: Use scripts/pcm_to_wav.py for audio format conversion" } ], "body": "Podcast Generation with GPT Realtime Mini\n\nGenerate real audio narratives from text content using Azure OpenAI's Realtime API.\n\nQuick Start\nConfigure environment variables for Realtime API\nConnect via WebSocket to Azure OpenAI Realtime endpoint\nSend text prompt, collect PCM audio chunks + transcript\nConvert PCM to WAV format\nReturn base64-encoded audio to frontend for playback\nEnvironment Configuration\nAZURE_OPENAI_AUDIO_API_KEY=your_realtime_api_key\nAZURE_OPENAI_AUDIO_ENDPOINT=https://your-resource.cognitiveservices.azure.com\nAZURE_OPENAI_AUDIO_DEPLOYMENT=gpt-realtime-mini\n\n\nNote: Endpoint should NOT include /openai/v1/ - just the base URL.\n\nCore Workflow\nBackend Audio Generation\nfrom openai import AsyncOpenAI\nimport base64\n\n# Convert HTTPS endpoint to WebSocket URL\nws_url = endpoint.replace(\"https://\", \"wss://\") + \"/openai/v1\"\n\nclient = AsyncOpenAI(\n websocket_base_url=ws_url,\n api_key=api_key\n)\n\naudio_chunks = []\ntranscript_parts = []\n\nasync with client.realtime.connect(model=\"gpt-realtime-mini\") as conn:\n # Configure for audio-only output\n await conn.session.update(session={\n \"output_modalities\": [\"audio\"],\n \"instructions\": \"You are a narrator. Speak naturally.\"\n })\n \n # Send text to narrate\n await conn.conversation.item.create(item={\n \"type\": \"message\",\n \"role\": \"user\",\n \"content\": [{\"type\": \"input_text\", \"text\": prompt}]\n })\n \n await conn.response.create()\n \n # Collect streaming events\n async for event in conn:\n if event.type == \"response.output_audio.delta\":\n audio_chunks.append(base64.b64decode(event.delta))\n elif event.type == \"response.output_audio_transcript.delta\":\n transcript_parts.append(event.delta)\n elif event.type == \"response.done\":\n break\n\n# Convert PCM to WAV (see scripts/pcm_to_wav.py)\npcm_audio = b''.join(audio_chunks)\nwav_audio = pcm_to_wav(pcm_audio, sample_rate=24000)\n\nFrontend Audio Playback\n// Convert base64 WAV to playable blob\nconst base64ToBlob = (base64, mimeType) => {\n const bytes = atob(base64);\n const arr = new Uint8Array(bytes.length);\n for (let i = 0; i < bytes.length; i++) arr[i] = bytes.charCodeAt(i);\n return new Blob([arr], { type: mimeType });\n};\n\nconst audioBlob = base64ToBlob(response.audio_data, 'audio/wav');\nconst audioUrl = URL.createObjectURL(audioBlob);\nnew Audio(audioUrl).play();\n\nVoice Options\nVoice\tCharacter\nalloy\tNeutral\necho\tWarm\nfable\tExpressive\nonyx\tDeep\nnova\tFriendly\nshimmer\tClear\nRealtime API Events\nresponse.output_audio.delta - Base64 audio chunk\nresponse.output_audio_transcript.delta - Transcript text\nresponse.done - Generation complete\nerror - Handle with event.error.message\nAudio Format\nInput: Text prompt\nOutput: PCM audio (24kHz, 16-bit, mono)\nStorage: Base64-encoded WAV\nReferences\nFull architecture: See references/architecture.md for complete stack design\nCode examples: See references/code-examples.md for production patterns\nPCM conversion: Use scripts/pcm_to_wav.py for audio format conversion" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/thegovind/podcast-generation", "publisherUrl": "https://clawhub.ai/thegovind/podcast-generation", "owner": "thegovind", "version": "0.1.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/podcast-generation", "downloadUrl": "https://openagent3.xyz/downloads/podcast-generation", "agentUrl": "https://openagent3.xyz/skills/podcast-generation/agent", "manifestUrl": "https://openagent3.xyz/skills/podcast-generation/agent.json", "briefUrl": "https://openagent3.xyz/skills/podcast-generation/agent.md" } }