Imagine being able to understand what is said in videos or audio from foreign languages and having your own personal translator, helping you discover what was said through speech recognition. With the help of Tess AI, this is possible.
In this tutorial, we will explore one of the User Inputs in detail. This content is classified as intermediate, so it is essential that you have completed at least the Text Templates Tutorial. If you haven't done so yet, you can access it by clicking here.
If you have already read it, we estimate that you already have basic knowledge about creating templates, so we can move a bit further and dive deeper into this topic of input groups.
To begin your journey with Tess AI, in this tutorial we will cover each of the options below and their applications in the “Upload File” field.
Short Text Field: when selecting this type, you enable the user to type short texts for more objective answers.
Long Text Field: it allows the user to insert large blocks of text, in case your template requires a large amount of information.
Dropdown: allows you to create a single selection box, where the user chooses one of the options.
Multiple Choice: allows you to create a multiple selection box, where the user can select more than one option.
File Upload: this is where you can upload your attached materials.
At this point, we will select the field for File Upload, as shown in the image below:
The field will be intended for situations where you want to upload audio or video files, documents, etc., making it a crucial functionality in everyday use, and it integrates perfectly with an AI Step, such as document reading, for example.
To recap the information that will help you organize and bring your template ideas to life, always keep the following steps in mind:
Create the idea;
Develop a prompt;
Test the prompt in Conversation Copilot;
Refine the prompt;
Create the template.
In this tutorial, we will continue from Step 5. If you need to review the previous steps, you can follow the step-by-step guide by clicking here.
For the initial setup: we will start by defining the type of AI (chat, image, text). The process is simple, and all you need to do is choose from the options. If desired, you can switch between AI models by filtering for a specific model. By default, the “All LLM” option will already be selected.
After that, we will move on to the more technical part of the creation process.
Idea: A template that can analyze an audio or video file in a foreign language and translate it into Portuguese. Just send the file and receive all the formatted content.
Approved Prompt: “Transcribe each word that is in the converted-file.
Important: do not invent or add words, show exactly what is in the audio. Then, translate everything into Portuguese [pt-BR]. Result:”
Note that we only specified one AI Step, which will be linked to the Input we will create below. Select the “Upload File” option and fill it out as usual. In this case, the input field will simply be called “File."
converted-file will be the product of an analysis of the file sent, and will require the input. As we will see below.
This process differs from other input groups because it involves the inclusion of an Advanced AI Step, so we will go through the step-by-step process to ensure you can follow along.
For this template, a step involving another AI, one for audio transcription, will be necessary so that the audio can be converted to text.
Thus, in “Advanced AI Steps,” select the “Audio Transcription” type, and give a name to the transcription, in this case, “Converted File.”
Finally, specify that the imported field is the “**File**,” which should have the same name as the created Input. In this way, whatever the user inputs into the field File will be transcribed. Make sure the step is set up as follows:
Note that if you do not use the AI Step between asterisks in the Prompt, nothing the user attaches will be used by the AI. Therefore, make sure it is filled in exactly as it was created, including the asterisks, or click “+” to auto-fill.
When your agent is ready, just click on “Save" and “Preview" if you want to test it. You can also find it in the AI Studio as a draft.
You can validate your prompt after approval by testing, editing, and refining it until it has your personal touch.
If you want to publish it, simply change the visibility in AI Studio. In this case, the agent is sent for approval.
This is yet another tutorial for creating models through Tess AI. Be sure to follow our updates and features as we continue to expand the possibilities of AI.
A world of possibilities awaits you—start creating your AI right now!
