AI Voice & Transcription Templates

This n8n workflow demonstrates an approach to parsing bank statement PDFs with multimodal LLMs as an alternative to traditional OCR. This allows for much more accurate data extraction from the document especially when it comes to tables and complex layouts. Multimodal Parsing is better than traditiona OCR because: * It reduces complexity and overhead by avoiding the need to preprocess the document into text format such as markdown before passing to the LLM. * It handles non-standard PDF formats which may produce garbled output via traditional OCR text conversion. * It's orders of magnitude cheaper than premium OCR models that still require post-processing cleanup and formatting. LLMs can format to any schema or language you desire!

This workflow automates the transcription of audio files from Google Drive using OpenAI's Whisper API, summarizes the transcribed text with GPT-4, and saves the summary to a new page in Notion. It streamlines the process of converting audio content into written summaries for easy access and organization.

This workflow shows how to download an image file from S3 and pass it on to Textract for text extraction.  The workflow uses two nodes: - **AWS S3**: This node will download a receipt file from S3 - **AWS Textract**: This node connects to Aamazon's Textract service to extract text from the receipt file

Automatically generate custom voice note for leads that have accepted your Linkedin invites with lemlist. Here is how it works: - When a lead in lemlist accepts your invite, the workflow is triggered in n8n - The 1st consists in using the companyDescription to build a relevant icebreaker for your lead. - Then we use 11labs to convert the text into a voice message. It will use your own voice if you train it. - Once the voice note is created, we upload in lemlist and attach it to the right Linkedin message step. Full guide can be found [HERE]( https://lempire.notion.site/Guide-upload-voice-note-in-lemlist-with-API-1c98af01a9d742e89a1772dd890af9ac?pvs=4)

This workflow automates **voice reminders** for upcoming appointments by generating a professional audio message and **sending** it to clients **via email** with the voice file attached. It integrates Google Calendar to track appointments, ElevenLabs to generate high-quality voice messages, and Gmail to deliver them efficiently. 

This workflow fetches news articles from the BBC website, filters them based on suitability for a podcast using Gemini LLM, and then generates a podcast script from the selected articles, converting it to speech using Hugging Face's text-to-speech model. The workflow automates the process of turning BBC news articles into engaging podcasts.

This workflow automates the process of sending **text-to-speech (TTS) voice calls** using API. It allows users to submit a form with the message content, recipient's phone number, voice type, and language, and then sends a voice call with the provided text. This workflow is a simple yet powerful way to automate text-to-speech voice calls using API. It’s ideal for notifications, reminders, or any scenario where voice communication is needed. Below is a breakdown of the workflow: ---