{"product_id":"whatsapp-video-to-voice-transcripts-with-gemini-n8n","title":"WhatsApp Video to Voice \u0026 Transcripts with Gemini | n8n","description":"\u003ch3\u003eTurn WhatsApp Videos into Text—or Reply with AI Voice Notes—Automatically (n8n)\u003c\/h3\u003e\n\u003cp\u003eThis n8n workflow listens for incoming \u003cstrong\u003eWhatsApp\u003c\/strong\u003e messages, converts \u003cstrong\u003evideo audio to MP3\u003c\/strong\u003e, transcribes it with \u003cstrong\u003eGoogle Gemini\u003c\/strong\u003e, and sends the \u003cstrong\u003etranscript back\u003c\/strong\u003e to the sender. It can also generate \u003cstrong\u003evoice notes\u003c\/strong\u003e from a \u003cstrong\u003e\/tts\u003c\/strong\u003e command using \u003cstrong\u003eFish Audio\u003c\/strong\u003e.\u003c\/p\u003e\n\n\u003ch3\u003eWhat this workflow does\u003c\/h3\u003e\n\u003cul\u003e\n  \u003cli\u003e\n\u003cstrong\u003eTriggers on new WhatsApp messages\u003c\/strong\u003e and extracts the sender number, message type, media URL, and text body.\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eIf the message includes video media\u003c\/strong\u003e:\n    \u003cul\u003e\n      \u003cli\u003eDownloads the video from WhatsApp.\u003c\/li\u003e\n      \u003cli\u003eCreates a \u003cstrong\u003eFreeConvert\u003c\/strong\u003e job to convert the media to \u003cstrong\u003eMP3\u003c\/strong\u003e.\u003c\/li\u003e\n      \u003cli\u003eUploads the video to FreeConvert, waits, then \u003cstrong\u003epolls job status\u003c\/strong\u003e until conversion completes.\u003c\/li\u003e\n      \u003cli\u003eDownloads the resulting \u003cstrong\u003eMP3\u003c\/strong\u003e, sets the audio MIME type, and transcribes the audio using \u003cstrong\u003eGoogle Gemini\u003c\/strong\u003e.\u003c\/li\u003e\n      \u003cli\u003eSends the transcription text back to the original sender via WhatsApp.\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eIf the message text contains \u003ccode\u003e\/tts\u003c\/code\u003e\u003c\/strong\u003e:\n    \u003cul\u003e\n      \u003cli\u003eCalls a sub-workflow that generates speech with \u003cstrong\u003eFish Audio\u003c\/strong\u003e.\u003c\/li\u003e\n      \u003cli\u003eUploads the audio to WhatsApp and returns it to the sender as an audio message.\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/li\u003e\n\u003c\/ul\u003e\n\n\u003ch3\u003eUse cases\u003c\/h3\u003e\n\u003cul\u003e\n  \u003cli\u003eTranscribe WhatsApp voice-style videos sent by customers into searchable text for support teams.\u003c\/li\u003e\n  \u003cli\u003eCreate instant multilingual-style voice replies: send \u003ccode\u003e\/tts\u003c\/code\u003e + your text and receive an audio response.\u003c\/li\u003e\n  \u003cli\u003eOperational notes from WhatsApp: convert media to transcription for CRM or internal review (output is sent back to the user).\u003c\/li\u003e\n\u003c\/ul\u003e\n\n\u003ch3\u003eTechnical details\u003c\/h3\u003e\n\u003cul\u003e\n  \u003cli\u003e\n\u003cstrong\u003eWhatsApp Cloud API\u003c\/strong\u003e: WhatsApp trigger + message upload\/send steps (requires phone number ID and credentials).\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eFreeConvert\u003c\/strong\u003e: video-to-\u003cstrong\u003eMP3\u003c\/strong\u003e conversion (requires FreeConvert API key; template currently uses a hard-coded Authorization header).\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eGoogle Gemini\u003c\/strong\u003e (Google PaLM): audio transcription.\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eFish Audio\u003c\/strong\u003e: text-to-speech for \u003ccode\u003e\/tts\u003c\/code\u003e via a sub-workflow.\u003c\/li\u003e\n  \u003cli\u003eWorkflow control uses nodes including \u003cstrong\u003eif\u003c\/strong\u003e, \u003cstrong\u003eset\u003c\/strong\u003e, \u003cstrong\u003ecode\u003c\/strong\u003e, \u003cstrong\u003ewait\u003c\/strong\u003e, and supporting steps (e.g., sticky note).\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp\u003e\u003cstrong\u003eReady to deploy:\u003c\/strong\u003e add WhatsApp, FreeConvert, Google Gemini, and Fish Audio credentials, configure your \u003cstrong\u003evoice ID\u003c\/strong\u003e for TTS, then enable the workflow.\u003c\/p\u003e","brand":"N8N Commerce","offers":[{"title":"Default Title","offer_id":45755361427635,"sku":"N8N-17723","price":61.99,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0749\/6279\/6723\/files\/lzXwLVbfF4I9MwjXMVYoh_60XNi0om.png?v=1785661587","url":"https:\/\/buyflowscripts.com\/products\/whatsapp-video-to-voice-transcripts-with-gemini-n8n","provider":"N8N Commerce","version":"1.0","type":"link"}