# Send discord voice memo upgrade 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": "discord-voice-memo-upgrade", "name": "discord voice memo upgrade", "source": "tencent", "type": "skill", "category": "通讯协作", "sourceUrl": "https://clawhub.ai/koto9x/discord-voice-memo-upgrade", "canonicalUrl": "https://clawhub.ai/koto9x/discord-voice-memo-upgrade", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/discord-voice-memo-upgrade", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=discord-voice-memo-upgrade", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "CHANGELOG.md", "index.js", "README.md", "UPLOAD.md", "package.json", "PATCH.md" ], "downloadMode": "redirect", "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/discord-voice-memo-upgrade" }, "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/discord-voice-memo-upgrade", "downloadUrl": "https://openagent3.xyz/downloads/discord-voice-memo-upgrade", "agentUrl": "https://openagent3.xyz/skills/discord-voice-memo-upgrade/agent", "manifestUrl": "https://openagent3.xyz/skills/discord-voice-memo-upgrade/agent.json", "briefUrl": "https://openagent3.xyz/skills/discord-voice-memo-upgrade/agent.md" } } ``` ## Documentation ### Overview This skill provides a core patch for Moltbot that fixes voice memo TTS auto-replies. The issue occurs when block streaming prevents the final payload from reaching the TTS synthesis pipeline. ### Type Core Patch / Documentation This is not a traditional plugin that extends functionality - it's a documentation package with patch files for core Clawdbot modifications. ### Use Case Use this if you're experiencing: Voice memos not triggering TTS responses TTS working for text messages but not audio messages TTS auto mode = "inbound" not functioning ### Method 1: Manual Patch (Recommended for Development) # 1. Locate your clawdbot installation CLAWDBOT_PATH=$(which clawdbot) CLAWDBOT_DIR=$(dirname $(dirname $CLAWDBOT_PATH)) # 2. Backup original files cp $CLAWDBOT_DIR/lib/node_modules/clawdbot/dist/auto-reply/reply/dispatch-from-config.js \\ $CLAWDBOT_DIR/lib/node_modules/clawdbot/dist/auto-reply/reply/dispatch-from-config.js.backup cp $CLAWDBOT_DIR/lib/node_modules/clawdbot/dist/tts/tts.js \\ $CLAWDBOT_DIR/lib/node_modules/clawdbot/dist/tts/tts.js.backup # 3. Apply patch cp patch/dispatch-from-config.js $CLAWDBOT_DIR/lib/node_modules/clawdbot/dist/auto-reply/reply/ cp patch/tts.js $CLAWDBOT_DIR/lib/node_modules/clawdbot/dist/tts/ # 4. Restart clawdbot clawdbot restart ### Method 2: Wait for Upstream If this patch gets accepted into core Clawdbot, you can simply update: npm install -g clawdbot@latest ### Configuration No additional configuration needed beyond existing TTS settings. Ensure you have: { "messages": { "tts": { "auto": "inbound", // or "always" "provider": "openai", // or "elevenlabs" or "edge" "elevenlabs": { "apiKey": "your-key-here" } } } } ### How to Test Configure TTS with auto: "inbound" Send a voice memo to your bot Check logs for debug output: [TTS-DEBUG] inboundAudio=true ttsAutoResolved=inbound ttsWillFire=true [TTS-APPLY] PASSED all checks, proceeding to textToSpeech [TTS-SPEECH] ... Verify bot responds with audio ### Debug Logging The patch includes extensive debug logging. To view: # Logs will show in your clawdbot console clawdbot gateway start Look for: [TTS-DEBUG] - Shows TTS detection logic [TTS-APPLY] - Shows TTS payload processing decisions [TTS-SPEECH] - Shows TTS synthesis attempt ### Production Deployment Important: Before deploying to production, consider: Remove debug logging - The console.log statements should be removed or made configurable Test thoroughly - Ensure voice memos work correctly Monitor performance - Disabling block streaming may impact streaming behavior To remove debug logging, edit the patched files and remove lines containing: console.log('[TTS-DEBUG]' console.log('[TTS-APPLY]' console.log('[TTS-SPEECH]' ### Reverting If you need to revert the patch: # Restore backups CLAWDBOT_PATH=$(which clawdbot) CLAWDBOT_DIR=$(dirname $(dirname $CLAWDBOT_PATH)) cp $CLAWDBOT_DIR/lib/node_modules/clawdbot/dist/auto-reply/reply/dispatch-from-config.js.backup \\ $CLAWDBOT_DIR/lib/node_modules/clawdbot/dist/auto-reply/reply/dispatch-from-config.js cp $CLAWDBOT_DIR/lib/node_modules/clawdbot/dist/tts/tts.js.backup \\ $CLAWDBOT_DIR/lib/node_modules/clawdbot/dist/tts/tts.js clawdbot restart ### The Problem Block streaming is used to send incremental text chunks to the user as they're generated. However, TTS synthesis hooks into the "final" payload type by default. When block streaming is enabled: Text chunks are sent as "block" payloads The final assembled text is sent as a "final" payload But block streaming optimization drops the final payload (text already sent) TTS never fires because it only processes "final" payloads ### The Solution The patch adds detection logic to identify when TTS should fire: Inbound message has audio attachment (isInboundAudioContext()) TTS auto mode is "inbound" or "always" Valid TTS provider and API key configured When these conditions are met, block streaming is temporarily disabled for that specific reply, ensuring the final payload reaches the TTS pipeline. ### Code Flow dispatchReplyFromConfig() ├─ isInboundAudioContext(ctx) → detects audio ├─ resolveSessionTtsAuto(ctx, cfg) → gets TTS settings ├─ ttsWillFire = conditions met? └─ getReplyFromConfig({ disableBlockStreaming: ttsWillFire }) └─ maybeApplyTtsToPayload() receives final payload └─ textToSpeech() synthesizes audio ### Compatibility Clawdbot: 1.0.0+ Node.js: 18+ Platforms: All platforms supported by Clawdbot ### Known Issues Debug logging is verbose (should be removed for production) Modifies compiled dist files (not source) May need to reapply after clawdbot updates ### Contributing To improve this patch: Test with different TTS providers (OpenAI, ElevenLabs, Edge) Test with different auto modes ("always", "inbound", "tagged") Suggest optimizations to reduce debug logging overhead Propose integration into core Clawdbot source ### Support If you encounter issues: Check logs for [TTS-DEBUG] output Verify TTS configuration is correct Ensure API keys are valid Check that block streaming was actually disabled (disableBlockStreaming: true in logs) ### License Same as Moltbot. ## Trust - Source: tencent - Verification: Indexed source record - Publisher: koto9x - Version: 1.0.0 ## Source health - Status: healthy - Source download looks usable. - Yavira can redirect you to the upstream package for this source. - Health scope: source - Reason: direct_download_ok - Checked at: 2026-04-30T16:55:25.780Z - Expires at: 2026-05-07T16:55:25.780Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/discord-voice-memo-upgrade) - [Send to Agent page](https://openagent3.xyz/skills/discord-voice-memo-upgrade/agent) - [JSON manifest](https://openagent3.xyz/skills/discord-voice-memo-upgrade/agent.json) - [Markdown brief](https://openagent3.xyz/skills/discord-voice-memo-upgrade/agent.md) - [Download page](https://openagent3.xyz/downloads/discord-voice-memo-upgrade)