We realized a long time ago that Siri is not smart and quick-witted. It would seem that Apple’s voice assistant has been able to speak Russian for more than 6 years. It was possible to get rid of all sorts of bugs a long time ago and learn to answer trivial questions, but no, the Cupertino people still cannot make this function work as real voice assistants should. You can, of course, refer to the difficulty of implementing technology and other subtleties, but once you talk to Alice at least once, it immediately becomes clear that Apple employs real slackers. In this article I propose to talk in detail about the worst voice assistant from the best company.
We talk about the nuances of Siri that everyone should know.
Despite all the errors of Siri , it is still possible to find proper use for it. In my previous articles, I already talked about the use I found for a branded voice assistant. If you are not yet familiar with the material, be sure to read it.
Siri does not respond on iPhone: what to do
What is a voice assistant
A voice assistant is an Artificial Intelligence-based program that can recognize human speech, provide voice responses, and execute specific commands.
Imagine, your devoted friend is always next to you, who is ready to talk to you at any time of the day or night, answer any of your questions and carry out instructions. At the same time, he never gets tired, he is never in a bad mood, and every day he becomes smarter and understands you better. These are voice assistants that are available for everyday use today.
Voice assistants and smart speakers in which they “live”
Voice assistants are built into computers, tablets, phones, smartwatches, smart speakers, and even cars. It is important to understand that interaction with the voice assistant is carried out exclusively by voice, without using your hands, without pressing any buttons. This is a fundamentally new way of interaction between a person and a program, which is very similar to communication between people.
Giving commands with your voice is especially convenient when your hands are busy: while cooking, while jogging, while driving, or when you just don’t want to get out of bed to turn off the light.
In addition, voice assistants significantly improve the quality of life of people with disabilities by helping them interact with the world around them.
Among all existing voice assistants we can highlight:
- Apple's Siri
- Google Assistant by Google
- Amazon's Alexa
- Bixby from Samsung
- Alice from Yandex
- Marusya from VK (Mail.ru Group)
- Salute from Sberbank
We have already written about Alice and Google Assistant, and in this article we will talk in detail about Siri.
Working with quantities and mathematics
With Siri it is convenient to convert any values. Ask your assistant to do this. It works with the main parameters: volume, weight, length, area, time indicators, currency.
The virtual assistant can't handle complex math problems, but it can handle simple arithmetic. In this case, it can be called a convenient calculator that solves several actions at once. Simple examples:
- what is 30 divided by 3?
- 40 percent of 340;
- 455 plus 678 times 4.
Voice assistant Siri
Siri is a voice assistant that was the first to support the Russian language, and only then did the domestic Alice from Yandex appear, released at the end of 2022, and even later, in the summer of 2022, Google Assistant spoke in Russian. Siri recognizes Russian speech quite well, even if music is playing nearby or there are extraneous noises.
Siri on iPhone SE
Siri wasn't always owned by Apple. Initially, it was a separate application in the App Store for iOS. In 2010, Apple acquired Siri Inc. and their unique development. Shortly after the purchase, Apple built Siri into the iPhone 4S and then into its subsequent devices. Then, in 2011, Siri became the first product on the personal voice assistant market.
Siri adapts to each user individually, studies his preferences and begins to better understand his “master”. This is primarily noticeable in the improvement of your voice recognition after the first weeks of use. You can also tell Siri how to address you and the names of your contacts in your address book, so it can understand you better. And when Siri pronounces names incorrectly, you can always correct her and show her the correct accent.
Siri is available on iPhone, iPad, Mac, Apple Watch, Apple TV and HomePod, as well as in almost all modern cars via CarPlay. The way you launch Siri and the list of available commands varies depending on your device.
Technologies used
In order to better understand what Siri can do, we present you a list of partner technologies that are integrated into the agent:
Information about films, books, reviews - The NYT, Rotton Tomatoes, Movietickets.
- Weather – Yahoo Weather.
- Registers and business activity – Inc, Yandex, Localize, Yahoo local.
- Web search – Google, Bing, Yahoo.
- There is also functionality from CityShearch, Yelp, AndreGayot, OpenTable, BooRah.
All functionality is closely related and interacts with each other.
How to launch Siri on iPhone, iPad and iPod touch
Launch by pressing the Home button
Siri is available on all iPhones starting with iPhone 4s and running iOS 5 and higher. To launch Siri on iPhone (except iPhone X), you need to press and hold .
To launch Siri on iPhone X, you need to press and hold the side button.
After the beep, you can make a request. On some devices, you must wait for Siri to appear on the screen before giving a command.
Internet resources and program capabilities
Commands for Siri in Russian can be set by any user, simplifying the process of sending email, making video calls, and searching for information on the Internet. The assistant will find the book, document, audio file or video you need. Even making posts on social networks is easier and more convenient.
A request regarding the search for specific information can be specified as much as possible. Examples:
- find on the Internet (general phrase);
- find it on Wikipedia;
- find it on Google;
- find news.
It is worth mentioning separately the interaction with the iTunes service. Siri guesses the music and can find it on the Web. This also applies to other files.
Hey Siri - How to enable Siri with your voice
Siri can be launched solely using your voice, without pressing any buttons at all. All you have to do is say, “Hey Siri.” After the sound signal, you can ask a question or give a command.
To do this, the “Hey Siri” function must be activated on the device: Settings → Siri and search → Listen to “Hey Siri”.
On all iPhone models, starting with the iPhone 6s, as well as on the iPad Pro, this function can be used at any time by saying “Hey Siri” so that the gadget’s microphones can pick it up. On earlier iPhones and iPads, the always-listening feature only works when your device is connected to a charger.
Oleg from Tinkoff
Tinkoff Bank now has a personal electronic assistant “Oleg”. It is integrated into the bank's mobile applications after update 4.8 for iOS. The founder of the company O. Tinkov gave a presentation of the assistant in December 2022.
Artificial intelligence manages the finances of bank clients, helps plan and manage them. “Oleg” is a polite and competent young “man”.
He helps:
- transfer money;
- looking for discounts;
- books tables in cafes, tickets to theaters, registers for swimming pools, hairdressers;
- manages bank cards;
- works with email;
- advises on financial issues;
- talks and entertains the client.
Likes and dislikes for completed work help the application better understand the user’s priorities.
When “Oleg” cannot answer, he calls the bank manager. At this time, he himself collects the necessary information and passes it on to the employee.
“Oleg” develops skills in the user’s speech style and adapts to the type of conversation. Soon they speak "as equals."
Download and launch the application from the bank’s official website. The request begins with the words “Hello, Oleg!”, or “Listen, Oleg!”.
The call centers of Sberbank, VTB, Alfa-Bank also successfully use virtual assistants. They replace real employees by 25%.
How to enable Siri on headphones
Using an original Apple headset with remote control buttons or compatible Bluetooth headphones, you can activate Siri by pressing the center button or the call button. After the beep, you can make a request.
When using Apple's wireless AirPods, double -tap the outside of either earbud to launch Siri.
Instructions for use
To simplify their work processes, install the Alice application - download the bot from the developer’s website.
Algorithm for PC:
- open the developer page;
- click “Download”;
- waiting to download to PC;
- click “Install”;
- follow the system's instructions.
Algorithm for phones:
- click on the link of the official application page;
- choose your own system on your mobile;
- open an application store;
- type a request;
- Select the program and click “Install”.
iPhone owners cannot install the application. But you can download it to your smartphone from the Play Market. The Alice voice assistant is installed free of charge.
Siri on Mac
Siri is available on Mac computers running macOS 10.12 Sierra and later versions of the operating system. However, at the moment the functionality of the voice assistant on the Mac is limited. All Siri can do here is make FaceTime calls, write messages, play music, show the weather forecast and help you work with files and folders.
Siri on Mac
It is worth noting that working with files on a computer using a voice assistant is really convenient. Siri can quickly search for files, sort them by type, date or keyword. For example, if you tell Siri, “Show me my photos from yesterday,” a folder with the corresponding media files will open.
There are several ways to activate Siri on Mac:
- Click the Siri icon in the menu bar (upper right corner).
- Press and hold the Command (⌘) key and the Spacebar key at the same time (provided that this key combination has not been reassigned).
Launching using the voice command “Hey Siri” does not yet work on computers. There is a workaround to set up this type of activation through the Dictation function, but we do not recommend it.
There will likely be more commands for Siri in future versions of macOS, including commands for HomeKit. This would be a logical continuation of Apple's integration of voice assistant into its laptops and desktops.
Most popular queries
Siri's capabilities in terms of controlling device functions and modes are practically unlimited. Here are examples:
- increase the player volume;
- reduce screen brightness;
- enable energy saving mode;
- open settings with notifications;
- turn on Wi-Fi;
- turn on bluetooth;
- enable silent mode;
- open notification settings.
Siri's basic skills are to work with calls and messages. The program can be “taught” to distinguish even family ties. Here are the commands that are most often used:
- dial mom;
- dial a number (the user dictates a combination of numbers);
- dial a message to Sasha;
- show messages from Lena.
Fast start
- Download the project from Github
- To quickly install all the required dependencies, you can use the command: pip install -r requirements.txt
- To start, run the runva_vosk.py from the root folder. By default, it will launch the vosk offline recognizer for speech recognition from the microphone, and the pyttsx voiceover engine for the assistant (the standard Windows speech synthesis engine).
- After launch, you can check with a simple command - say “Irina, hello!” into the microphone
Our own Text-to-Speech and Speech-to-Text engines
By default, the VOSK engine is used for speech recognition, and Windows (Irene's voice) is used for synthesis.
It is quite possible to add your own options; this is a standard operation. Details are on Github.
STT is already available through the SpeechRecognition module (online recognition from Google, etc.), as well as TTS through Silero (offline neural network generation). I didn't really like the result of Silero (although the project itself is beautiful) - it takes longer to generate, there is a delay of several seconds, and there are also "metallic" noises, but perhaps it will suit you. (By the way, in one of the comments @putnik shared his own analysis of the available TTS and STT engines.)
By the way, the name of the assistant is also configured in the configuration file - so if necessary, you can make it respond to the name “Jarvis”. And you can put a male voice, of course.
Your plugins
To be honest, I already have several of my own plugins purely for my own use.
For example, clicking “Irina, play music” opens Yandex.Music.
We also have a local, non-chain delivery provider of good pizza (PushPizza, if anyone is interested). In about half an hour, I wrote a plugin that checks the state of the delivery - being prepared or on the way. An algorithm was written using the pyautogui , which allows you to emulate user input (mouse and keyboard):
- Open delivery page
- Wait a little bit
- Find a picture on the screen (phone input form) (yes, pyautogui has this out of the box)
- Move your mouse there and click
- Simulate phone input
- Voila! Delivery status page available
In general, writing plugins seemed to be easy. (If you suddenly write something and want to share, you can post links here.
Ready plugins
Irina comes with plugins that cover most of the usual cases of using a voice assistant (unless, of course, you intend to communicate with it). For each plugin it is written whether online is required. To disable it, remove it from the folder.
plugin_greetings.py - greeting (offline). Example command: “Irina, hello”
plugin_timer.py - timer (offline). Examples: “timer, timer six minutes, timer ten seconds, timer ten” (without specifying units, sets for minutes - “timer ten” - for ten minutes. Simply “timer” sets for five minutes)
plugin_mediacmds.py - media control commands (offline). Example: “further, louder, quieter, much louder, much quieter, pause.” (If mpcIsUseHttpRemote is set, then an attempt is first made to call the MPC-HC player command; if this fails, multimedia key emulation is used)
plugin_mpchcmult.py - play cartoons via MPC-HC from a specific folder (offline). Example “cartoon <cartoon_name>”. The folder is specified in the config. When you call the command, a file with the corresponding name <cartoon_name> and any extension is searched in the folder. If found, it starts playing. (As you might guess, this plugin is designed to display selected media without accessing YouTube.)
plugin_random.py - random (offline). Examples: “toss|toss a dice|a coin.” Contains examples of parsing a command tree (commands can be specified as a tree). More of a demo plugin.
plugin_weatherowm.py - weather (online). Examples: “weather, weather tomorrow, weather the day after tomorrow, weather forecast.” Requires installation of a free API key from here in the config, as well as the user's location.
plugin_yandex_rasp.py — schedule of the nearest trains via Yandex.Schedules. Example: “train, trains.” Requires installation in the config of a free API key for personal needs (up to 500 requests per day) from here, as well as departure and destination stations. (If you travel by train, the phrase “Irina, train” is very convenient for checking the schedule)
plugin_tts_pyttsx.py - (offline) allows you to do TTS (Text-To-Speech, text voice acting) through the pyttsx engine. Used by default.
plugin_tts_console.py - (offline) debugging plugin. Instead of working, TTS simply prints text to the console.
