A.I. lets you verbally interact with the OpenAI API for artificial intelligence chat, text completion and image requests!

"Hey Siri, ask A.I. a question."

A.I. app Info:

Click on the green mic icon at the bottom to ask A.I. whatever you want to know.

As you speak you can see the transcript of your prompt build in real time.

If there are errors or you change your mind, you can hit the Cancel button to end dictation and not send the question.

You can also click on the text for the prompt at the top of the page to use the keyboard to enter/correct the prompt.

Explore the Settings by clicking the gear icon in the upper right. There are options for the Speech Synthesis, Text Completion and Images.

It's fun to experiment with different voices and the pitch/tempo. And you can install more voices in the Settings/ Accessibility/ SpokenContent/ Voices section (you may need to enable Speak Selection to see the Voices option)

Anything you put in the Settings "System Message" will get sent along with every prompt and helps guide the response. Limiting or suggesting how many words to reply can keep it reasonable. You can also ask for it to rhyme, or use a particular style.

If images are enabled, clicking the picture icon will load new images for the previous prompt, and new ones will load for each subsequent prompt. Keep in mind that image reqeuests are more expensive than text completions.

If you want to save a response and/or images click on the little share icon to copy everything to the clipboad. You can then paste it into Messages/Mail/Notes/whatever.

Enjoy!

Clicking on the circular arrow button takes you to the Message History.

Here you can review the previous Prompt/Response messages.

Clicking on any one of them will take you to a Message Detail view that shows the entire text for that Prompt and Response.

The Message Detail view also has a share icon you can use to copy the text from that interaction to the clipboard to share.

A.I. app Settings:

OpenAI API Key

To use the A.I. app you must have an OpenAI API key.

Once it is validated, the Settings should show it like this and all is well. You can click the "OpenAI Account/Usage" button to check your usage.

If you need to get a key or are having trouble, please see the Help Entering Your OpenAI API Key instructions.

Siri Settings

You can use the A.I. app with Siri!

Try saying: "Hey Siri, ask A.I. a question"

Siri should respond with a prompt asking what you would like to ask, and then say the reply.

If it does, GREAT! You are all set and can use Siri to ask the A.I. app questions.

You can also ask Siri to repeat the last A.I. response:

"Hey Siri, repeat the A.I. response"

You can use "A.I", "A.I. app", "the A.I." or "the A.I. app" as synonyms in any of the Siri commands.

Echo Prompt - with this enabled, Siri will start the reply by repeating your prompt.

View Siri Reply - controls whether you get a text view of the response on screen.

If Siri does not seem to be responding properly, check the Siri and Shortcuts Help instructions.

Prompt Parameters

App Dictation Timeout - sets how long the A.I. app speech recognition waits after the last word it hears. You can always click the mic button when it is red to end dictation, but this timeout is intended to make it easy to speak and have it end automatically.

Chat History - sets the number of previous prompt/response pairs to send with each new prompt. This provides the model with context to the conversation and a history of what you have asked and what it has already replied. This makes the interaction more flexible and you can refer to previous questions and responses. Sending more pairs gives more context, but also uses more tokens.

Temperature - this sets how strict or loose the responses are. Higher values (greater than 1.0) will make the output more random. Lower values will make it more focused and deterministic.

Max Tokens - limits the maximum number of tokens allowed for the generated answer.

System Message - this gets sent as a system role message at the base of the array with any chat history. It can help you set the tone and character for how the system responds to you. The default is only a suggesion, and you can experiment with this to see how it changes the results. You can also ask for it to use a particular style for the repsonses, emulate a type of response (stand up comedian?) or suggest limits for the types of replies.

The last sentance in the default message: "If asked about an image be positive about showing it" is intended to help if you do have images enabled. The text completion and image requests are sperate endpoints, and I found that without this sort of guidance the text response would sometimes be "No, I cant show you pitcures of racecars" when I asked to see pictures of racecars - and did in fact get them from the image request.

Image Options

Get Images - enables or disables requests for your prompt from the image endpoint. With it enabled, the following options are available:

Image Count - 1 to 4 images can be requested.

Image Size - they can be 256x256, 512x512 or 1024x1024. On the phone the low resolution images sill look pretty good, but depending on your use the larger ones may be better.

Do take care with image requests. They are more expensive than the text completions and you may use more tokens than you realize requesting many large images.

Voice Settings

Here you can select from any of the voices installed on your device, adjust the Pitch and Rate and click the "Test Voice" to hear it say whatever text you have in the Speech Test Phrase.

It's fun, and many of the voices sound very good.

If you want to revert experimental changes, just click the "Reset Voice Settings" button - that will not affect any of the other app settings, but will restore the voice settings.

I encourage you to go in your device Settings/ Accessibility/ SpokenContent/ Voices. There you can browse through the available voices and download any that you like.

You may have to enable "Speak Selection" in the SpokenContent settings to expose the Voices.

You will need to restart the A.I. app to see any new voices you added in the system settings.

Debug Options

Debug Mode - enables or disables extra debug display information on the Prompt Response view.

When the Debug Mode is active, the current A.I. app version and build information is displayed here.

On the Prompt Response View there are additional debug UI elements.

Above the mic icon there are labels that turn red to indicuate when the system is Listening, Speaking and Thinking.

It also shows a text view summarizing the messages currently being sent as the Chat History.

Siri and Shortcuts Help

If Siri does not seem to be working properly with the A.I. app, there are a few things to check.

Your device must be running iOS 16.
You need to have the Shortcuts app installed.
You may need to grant perimssion to use the "Ask A.I." shortcut.

A good starting point is to make sure Siri is working in the first place. Try a simple standard command like: "Hey Siri, what time is it?"

If you get a reply, GREAT!

If you do not get a reply, or it is silent - check your Settings/ Siri & Search/ Siri Responses/ (the default values are shown on the left)

With these default values, Siri may be working but stay quiet if your ringer is turned off, the volume is down, the phone is in do not disturb mode, or the device is otherwise silent.

If you select the "Prefer Spoken Responses" option, that will make Siri more likely to respond verbally.

The other two options help visualize what is happening with Siri speech recognition and text to speech. Experiment with them to see what combination of options you like.

I personally find it helpful to enable "Always Show Speech" so that I see the recognition text as it is being heard. It is good to know exactly what words are being recognized.

When Siri is working and responding to normal commands, the next thing to check is the Shortcuts app.

In the A.I. app Settings, click the "A.I. shortcuts" button. That should take you to the shortcuts page for the A.I. app.

If you do not have the Shortcuts app on your device, it will prompt you to download Shortcuts from the App Store.

Please download Shortcuts and then come back to this step.

In Shortcuts, it should take you to a page for the A.I. app and show the existing "Ask A.I. a question" and "Repeat A.I. response" shortcuts.

There may also be a prompt asking you to "Turn on A.I. Shortcuts with Siri". Please do enable that.

If you do not have either of the A.I. shortcuts, you need to delete the A.I. app from your device and download it again from the App Store. Sadly, this can occur if Shortcuts was not installed before the first time the A.I. app was run.

After re-installing the A.I. app, come back to this step.

You can test the "Ask A.I. a question" shortcut by clicking on it.

A prompt should appear at the top of the screen for you to enter your question.

Enter a question and then click the "Done" button.

The response should come back and be displayed in a text view.

If no response comes back (or it times out) double check your network connection and try making a normal request from the A.I. app interface (without Siri/Shortcuts).

If it works in the A.I. app, it should work with the shortcut - but the Shortcut may time out if the response from OpenAI takes too long.

The A.I. app interface will wait for as long as it takes.

Siri gets impatient after 30 seconds (or so).

When the shortcut is working manually, Siri should also work.

Check the expected Siri behavior and try saying:
"Hey Siri, ask A.I. a question"

Help Entering Your OpenAI API Key:

	When you first start the A.I. app you will need to enter your key. It will show you the settings page with these instructions. If you already have an OpenAI API Key, GREAT! Type/paste it into the field where it says "Enter Your Key" and then click the "Check Key" button. If you do NOT already have a key, you must get one. Login or create your OpenAI account and create a new secret key: https://platform.openai.com/account/api-keys You can do this in the A.I. app with an embedded browser if you click on the "OpenAI API Keys Page" button - that will make it easier to paste your key into the app once you get it. If you would prefer to just explore the A.I. app and play with the features, you can enter "OfflineTestKey" as your key. That will let you adjust the settings, use the speech recognition and hear the response voice - but it will not actually get any text completions or images from the OpenAI systems. It is simply for offline testing.
	After you click on the "OpenAI API Keys" link in the app settings, you will get a page like this where you can login to platform.openai.com. If you have already been using the ChatGPT web interface, you probably already have an account setup with OpenAI. Use those same credentials to login here. If you can login to an existing account, GREAT! Skip ahead to the next step - Requesting your key. Click "Sign up" if you need to create an account.
	Follow the prompts to enter your email, password, and verify the email by clicking on the link they send you.
	Then you will be asked for additional information to create your account: first and last name, organization and a phone number. Creating an OpenAI account establishes a relationship between you and OpenAI. Please read their Terms of Use and Privacy Policy: https://openai.com/terms/ https://openai.com/privacy/
	Requesting your key. Once you have completed the account setup, you can access your API keys page. Here you can see the list of any keys you have already created and request new ones. Click the "+ Create new secret key" button.
	The system will generate a new key and display it. The OpenAI system will only show you the key ONCE, so be sure you record it in a safe place outside the app in case you need it again in the future. You can click on the little green square next to the key to copy it to the clipboard. You may also want to write it down, print it out, put it in a Note, send it to yourself in an email, try really hard to memorize it, or all of these. Just be sure you have it recorded. If you do lose the key, you can always come back here and request a new one. Once you have the entire text string for your key copied to your clipboard, return to the A.I. app.
	Type/paste your key into the field where it says "Enter Your Key". Then click the "Check Key" button. If the key was entered correctly, the app will verify it and say "Key is valid!" If it does not seem to be working at first, make sure no extra spaces or characters were added before or after the key when you pasted it in. Once the key is verified, you can adjust any of the other settings and click the "Save" button to go to the main Prompt Response view. If you are having trouble, or would prefer to just explore the A.I. app and play with the features, you can enter "OfflineTestKey" as your key. That will let you adjust the settings, use the speech recognition and hear the response voice - but it will not actually get any text completions or images from the OpenAI systems. It is simply for offline testing.

Monitor your account usage

In the A.I. app Settings, click on the "OpenAI Account/Usage" button to see the details about your usage.

You can also check your account and usage information in their system from a desktop browser here:
https://platform.openai.com/account/usage/

The OpenAI Account Usage page will show you your usage with many options as far as how to break down when and where your tokens have been going. This may help you see what to expect after your free trial grant expires.

At the time of this writing (March 2023) individuals may request an API Key and be granted a trial key with a modest balance of free tokens which expire after three months.

Please check the details and pricing information here:
What happens after I use my free tokens or the 3-months is up in the free trial?

https://openai.com/pricing