# Send Speech to Text Transcription 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. 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. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "speech-to-text-transcription", "name": "Speech to Text Transcription", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/ivangdavila/speech-to-text-transcription", "canonicalUrl": "https://clawhub.ai/ivangdavila/speech-to-text-transcription", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/speech-to-text-transcription", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=speech-to-text-transcription", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "SKILL.md", "memory-template.md", "setup.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/speech-to-text-transcription" }, "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/speech-to-text-transcription", "downloadUrl": "https://openagent3.xyz/downloads/speech-to-text-transcription", "agentUrl": "https://openagent3.xyz/skills/speech-to-text-transcription/agent", "manifestUrl": "https://openagent3.xyz/skills/speech-to-text-transcription/agent.json", "briefUrl": "https://openagent3.xyz/skills/speech-to-text-transcription/agent.md" } } ``` ## Documentation ### Setup On first use, read setup.md and start helping with transcription needs. ### When to Use User has audio or video files that need transcription. Agent handles local files, URLs, voice memos, podcasts, interviews, meetings, and lectures. ### Architecture Memory lives in ~/speech-to-text-transcription/. See memory-template.md for structure. ~/speech-to-text-transcription/ ├── memory.md # Provider preferences, defaults ├── transcripts/ # Saved transcriptions └── temp/ # Processing workspace ### Quick Reference TopicFileSetup processsetup.mdMemory templatememory-template.md ### 1. Detect File Type First Before transcription, identify the input: Local file path → verify exists, check format URL → download to temp, then process Meeting recording → likely needs speaker diarization Voice memo → usually single speaker, shorter ### 2. Choose Provider Based on Context ScenarioBest ProviderWhyQuick local transcriptionWhisper (local)No API key, free, privateHigh accuracy neededOpenAI Whisper APIBest qualitySpeaker identificationAssemblyAINative diarizationReal-time/streamingDeepgramLow latencyLong content (>2 hours)Split + batchAvoid timeouts ### 3. Handle Long Audio Files over 25MB or 2 hours: Split into chunks (use ffmpeg) Process each chunk Merge transcripts with proper timestamps Never attempt single upload for large files ### 4. Preserve Context After transcription: Ask if user wants the transcript saved Suggest filename based on content Offer to extract action items or summary ### 5. Output Formats Default to plain text. Offer alternatives: .txt — clean text, no timestamps .srt / .vtt — subtitles with timing .json — structured with word-level timing .md — formatted with speaker labels ### Common Traps Assuming one provider works for all → Whisper fails on diarization, AssemblyAI needs API key Uploading huge files directly → Timeouts, memory errors. Split first. Ignoring audio quality → Noisy audio needs preprocessing (ffmpeg noise reduction) Not checking language → Whisper auto-detects but can fail on mixed-language content Losing speaker context → Multi-speaker content without diarization becomes unusable ### Requirements Required: ffmpeg (for audio processing) Optional API keys (only if using cloud providers): OPENAI_API_KEY — for OpenAI Whisper API ASSEMBLYAI_API_KEY — for AssemblyAI (speaker diarization) DEEPGRAM_API_KEY — for Deepgram (real-time) Local Whisper works without any API keys. ### Local Whisper (No API Key) # Install pip install openai-whisper # Basic transcription whisper audio.mp3 --model base --output_format txt # With timestamps whisper audio.mp3 --model medium --output_format srt Models: tiny (fast) → base → small → medium → large (accurate) ### OpenAI Whisper API curl -X POST https://api.openai.com/v1/audio/transcriptions \\ -H "Authorization: Bearer $OPENAI_API_KEY" \\ -H "Content-Type: multipart/form-data" \\ -F file="@audio.mp3" \\ -F model="whisper-1" ### AssemblyAI (Speaker Diarization) # Upload curl -X POST https://api.assemblyai.com/v2/upload \\ -H "Authorization: $ASSEMBLYAI_API_KEY" \\ --data-binary @audio.mp3 # Transcribe with speakers curl -X POST https://api.assemblyai.com/v2/transcript \\ -H "Authorization: $ASSEMBLYAI_API_KEY" \\ -H "Content-Type: application/json" \\ -d '{"audio_url": "URL", "speaker_labels": true}' ### Extract Audio from Video ffmpeg -i video.mp4 -vn -acodec pcm_s16le -ar 16000 -ac 1 audio.wav ### Reduce Noise ffmpeg -i noisy.wav -af "afftdn=nf=-25" clean.wav ### Split Long Audio # Split into 10-minute chunks ffmpeg -i long.mp3 -f segment -segment_time 600 -c copy chunk_%03d.mp3 ### Security & Privacy Data that stays local: Transcripts in ~/speech-to-text-transcription/transcripts/ Local Whisper processes entirely on-device Data that leaves your machine (if using APIs): Audio file sent to chosen provider (OpenAI, AssemblyAI, Deepgram) Transcript returned and stored locally This skill does NOT: Store API keys in plain text (use environment variables) Auto-upload without confirmation Retain files on external servers after processing ### External Endpoints EndpointData SentPurposeapi.openai.com/v1/audioAudio fileWhisper API transcriptionapi.assemblyai.com/v2Audio fileAssemblyAI transcriptionapi.deepgram.com/v1Audio streamDeepgram transcription Only called when user explicitly chooses cloud provider. Local Whisper sends nothing. ### Trust By using cloud transcription providers, audio data is sent to OpenAI, AssemblyAI, or Deepgram. Only install if you trust these services with your audio. For sensitive content, use local Whisper. ### Related Skills Install with clawhub install if user confirms: audio — General audio processing ffmpeg — Video and audio conversion podcast — Podcast creation and editing ### Feedback If useful: clawhub star speech-to-text-transcription Stay updated: clawhub sync ## Trust - Source: tencent - Verification: Indexed source record - Publisher: ivangdavila - 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/speech-to-text-transcription) - [Send to Agent page](https://openagent3.xyz/skills/speech-to-text-transcription/agent) - [JSON manifest](https://openagent3.xyz/skills/speech-to-text-transcription/agent.json) - [Markdown brief](https://openagent3.xyz/skills/speech-to-text-transcription/agent.md) - [Download page](https://openagent3.xyz/downloads/speech-to-text-transcription)