In this video, I walk you through the powerful new action added by OpenAI on Zapier: the Whisper Transcription Action.
Leveraging their Whisper API for highly accurate speech-to-text conversions, this action brings OpenAI’s cutting-edge technology for transcription right to your fingertips.
Not only does it allow you to create transcriptions from audio and video files up to 25 MB, but it also supports multiple languages and formats.
Watch as I explore the potential of this action to revolutionize your workflow, manage data more effectively, and integrate seamlessly with other tools like Google Docs and Trello. Don’t forget to like, comment, subscribe, and share your thoughts on how you plan to use this innovative addition to Zapier!
1:32 Context on Whisper API and its capabilities
3:08 Different voice models and benchmarks
4:36 Setting up the Whisper Transcription Action on Zapier
7:13 Testing action and output formats
8:54 Creating a Google Doc from transcription output
10:19 Importance of workflow enablement and potential disruption
11:45 Conclusion and invitation for feedback
Zapier on Twitter: “Zapier’s @OpenAI integration just shipped a new action: Create Transcription
Zapier's @OpenAI integration just shipped a new action: Create Transcription 🗣️
Powered by OpenAI's Whisper API, you can upload audio or video files up to 25 MB to convert spoken language into written text for multiple languages.
— Zapier (@zapier) April 21, 2023
List of ISO 639-1 codes – Wikipedia
Introducing ChatGPT and Whisper APIs
GitHub – openai/whisper: Robust Speech Recognition via Large-Scale Weak Supervision
Get transcription, research, data analysis and NLP software from Speak Ai
Embeddable Audio & Video Recorder – Speak Ai
Introducing Nova: World’s Most Powerful Speech-to-Text API – Deepgram Blog ⚡️
Meet the World’s Most Powerful Speech-to-Text API: Deepgram Nova. – YouTube
AK on Twitter: “Whisper JAX This repository contains optimized JAX code for OpenAI’s Whisper Model, largely built on the 🤗 Hugging Face Transformers Whisper implementation.
This repository contains optimized JAX code for OpenAI's Whisper Model, largely built on the 🤗 Hugging Face Transformers Whisper implementation. Compared to OpenAI's PyTorch code, Whisper JAX runs over 70x faster, making it the fastest Whisper implementation… pic.twitter.com/ei8xzIeWC7
— AK (@_akhaliq) April 22, 2023
GitHub – sanchit-gandhi/whisper-jax
Whisper JAX – a Hugging Face Space by sanchit-gandhi
Yohei on Twitter: “I’m still proud of the fact that I introduced LLMs to NoCode w this Zapier integration – which I built without permission (this eventually became the official integration). This was pre-ChatGPT!” / Twitter
I’m still proud of the fact that I introduced LLMs to NoCode w this Zapier integration – which I built without permission (this eventually became the official integration).
This was pre-ChatGPT! https://t.co/Tv9hENi1yz
— Yohei (@yoheinakajima) April 22, 2023
OpenAI And Zapier Release No Code Integration For GPT and DALL-E! – YouTube
Speak Ai Integrations | Connect Your Apps with Zapier
OpenAI (GPT-3 & DALL·E) Integrations | Connect Your Apps with Zapier
Whisper API FAQ | OpenAI Help Center