This example shows off how we at Gooey.AI have created and use our bot workflow to talk about our company does. Check out the settings to see the description used to power the bots personality.

Here we take an input sample of Kikuyu phrases (and their expert transcription and English translations) and compare the top Speech Reco and Translation models. As of Mar 25, 2025, we've found that Meta's MMS-Large works best for Kikuyu with Ghana NLP's Kikuyu to English translation services.

. Which AI model actually works best for your needs?
Upload your own data and evaluate any Gooey.AI workflow, LLM or AI model against any other.
Great for large data sets, AI model evaluation, task automation, parallel processing and automated testing.
To get started, paste in a Gooey.AI workflow, upload a CSV of your test data (with header names!), check the mapping of headers to workflow inputs and tap Submit.
More tips in the Details below.

Which AI model actually works best for your needs? Upload your own data and evaluate any Gooey.AI workflow, LLM or AI model against any other. Great for large data sets, AI model evaluation, task automation, parallel processing and automated testing. To get started, paste in a Gooey.AI workflow, upload a CSV of your test data (with header names!), check the mapping of headers to workflow inputs and tap Submit. More tips in the Details below.

Use this function to Log and return variables from any Gooey.AI workflow.

Our general bulk evaluator to compare AI generated copilot answers against a collection of golden Answers.

This run is useful if you are only interested in Regression testing, Monitoring and Evaluation, Observability and Bugs.

This recipe is used with https://gooey.ai/bulk to evaluate the latest private & open source speech recognition models (from Google, Meta, OpenAI and others). It takes a CSV file of golden (aka human provided) translations and compares those against a set of AI created translations to generate scores from 0 to 1. It then takes the mean of the scores to determine which model performed best.

Compare Swahili Speech Recognition and Translation to English with this run. We have 10 variations in this. Including the latest Seamless M4T v2, MMS, Azure, Whisper v3 and more.

Transcribe any YouTube, mp3, WhatsApp audio or wavs with the best of transcription and translation AI models from OpenAI (Whisper v2 & v3), Microsoft Azure, Google USM, Meta Seemless4MT, AI4Bharat, Bhashini, etc Optionally translate to any language too.

Transcribe any YouTube, mp3, WhatsApp audio or wavs with the best of transcription and translation AI models from OpenAI (Whisper v2 & v3), Microsoft Azure, Google USM, Meta Seemless4MT, AI4Bharat, Bhashini, etc Optionally translate to any language too.

This example collects all the parameters (the user's query, the bot's answer, WhatsApp number number, etc) from the copilot workflow and sends it to an arbitrary endpoint. Alter this example with the REST API of your own server to log every interaction.

A Bot for Opportunity.org that gives advice to Malawi farmers and extension agents based on a guideline PDF from the Ministry of Agriculture. Support incoming pictures of sick plants, understands English and is connected to WhatsApp bots as well.

Here we take an input sample of Kikuyu phrases (and their expert transcription and English translations) and compare the top Speech Reco and Translation models. As of Sep 23, 2024, we've found that Meta's MMS-Large works best for Kikuyu with Ghana NLP's Kikuyu to English translation services.

. Which AI model actually works best for your needs?
Upload your own data and evaluate any Gooey.AI workflow, LLM or AI model against any other.
Great for large data sets, AI model evaluation, task automation, parallel processing and automated testing.
To get started, paste in a Gooey.AI workflow, upload a CSV of your test data (with header names!), check the mapping of headers to workflow inputs and tap Submit.
More tips in the Details below.

Transcribe mp3, WhatsApp audio + wavs with OpenAI's Whisper or AI4Bharat / Bhashini ASR models. Optionally translate to any language too.

Transcribe mp3, WhatsApp audio + wavs with OpenAI's Whisper or AI4Bharat / Bhashini ASR models. Optionally translate to any language too.

Transcribe mp3, WhatsApp audio + wavs with OpenAI's Whisper or AI4Bharat / Bhashini ASR models. Optionally translate to any language too.

Here we take an input sample of Kikuyu phrases (and their expert transcription and English translations) and compare the top Speech Reco and Translation models. As of Sep 23, 2024, we've found that Meta's MMS-Large works best for Kikuyu with Ghana NLP's Kikuyu to English translation services.

. Which AI model actually works best for your needs?
Upload your own data and evaluate any Gooey.AI workflow, LLM or AI model against any other.
Great for large data sets, AI model evaluation, task automation, parallel processing and automated testing.
To get started, paste in a Gooey.AI workflow, upload a CSV of your test data (with header names!), check the mapping of headers to workflow inputs and tap Submit.
More tips in the Details below.

Transcribe mp3, WhatsApp audio + wavs with OpenAI's Whisper or AI4Bharat / Bhashini ASR models. Optionally translate to any language too.

Transcribe mp3, WhatsApp audio + wavs with OpenAI's Whisper or AI4Bharat / Bhashini ASR models. Optionally translate to any language too.

Which AI model actually works best for your needs?
Upload your own data and evaluate any Gooey.AI workflow, LLM or AI model against any other.
Great for large data sets, AI model evaluation, task automation, parallel processing and automated testing.
To get started, paste in a Gooey.AI workflow, upload a CSV of your test data (with header names!), check the mapping of headers to workflow inputs and tap Submit.
More tips in the Details below.

Gooey.AI's Copilot is the best chatbot builder anywhere, combining your choice of LLMs (GPT4o, GPT4o-mini, Gemini, Claude3.5, Mixtral or LLaMA3), knowledge docs from any link or doc/PDF (with table support!), speech recognition, text-to-speech and Lipsync, editable synthetic data pipelines, built in 👍🏿 👎🏼 feedback, conversation analysis, WhatsApp, slack, Facebook and API integrations and much more.

In this example, we present Farmer.CHAT. It uses a collection of documents and transcripts of 100s of videos representing best practices to answer common questions from Indian farmers. We load these documents + transcripts into a vector database. With each question, we search the vector DB and then add the results to a GPT script below to create an answer to the farmer's questions. Simply change the Instructions and Knowledge docs & tap Submit and then Save to make it your own.

To know more, head over to our COPILOT HELP GUIDE