Browse our comprehensive FAQ section to quickly find solutions, learn how to use ChatMaxima features, and get step-by-step guidance for setup, integrations, and support.
The audio block allows users to upload an audio file through the chatbot, which can then be converted into text.
The audio block is useful for collecting voice messages or spoken responses from customers, which is a convenient alternative to typing.
The bot uses a "Speech to Text Provider" and a specific "Speech to Text Model" to convert the audio into a text transcript.
You can use the "Prompt text to guide users" field to provide instructions on what type of audio they need to upload.
A "Speech to Text Provider" is the service that the bot uses to perform the audio-to-text conversion. The available options may vary depending on your bot's mode.
A "Speech to Text Model" is a specific AI model provided by the chosen service that performs the conversion. You can select the model that best suits your needs.
You need to select credentials to securely connect your chatbot to the chosen Speech to Text provider. The credentials must match the provider and model you have selected.
You can save the transcribed text by entering a name in the "Store the response in variable" field.
After you have filled in all the necessary fields, you must click submit to save the block.
You can use the audio block for use cases such as transcribing customer feedback, allowing users to submit voice notes, or for simple voice commands.
You can find the audio block by navigating to Dashboard → Quick Access. Then, under ChatMaxima Studio, click on Create Chatbot. The audio block will be available in the response section of the builder.
To find a video tutorial for the audio block, navigate to Dashboard → Resources. In the dropdown menu, click on Video Tutorial, and then use the search bar to find the specific guide.
link: https://chatmaxima.com/video-tutorials/using-the-response-audio-block-in-chatmaxima/
The transcribed text is stored in the variable you named, which you can then use to process the user's request. The original audio file is processed by the selected provider and then its content is saved as text.