google speech kit

Navigation Menu

Search code, repositories, users, issues, pull requests..., provide feedback.

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly.

To see all available qualifiers, see our documentation .

• Notifications You must be signed in to change notification settings

Documentation page for GoogleSpeechKit unreal engine plugin

IlgarLunin/UE4GoogleSpeechKit-docs

Folders and files, repository files navigation.

• UE4 Google Speech Kit

This is UE4 wrapper for Google's Cloud Text-to-Speech and syncronous Cloud Speech-to-Text speech recognition.

Plugin was battle tested in several commercial simulator projects. It is small, lean and simple to use.

• Table of contents

Engine preparation

Cloud preparation, speech synthesis, voice capture and speech recognition, percentage based string comparison (fuzzy matching), listing available capture devices, supported platforms, version 3.0.

To make microphone work, you need to add following lines to DefaultEngine.ini of the project.

To not loose pauses in between words, you probably want to check silence detection treshold voice.SilenceDetectionThreshold , value 0.01 is good. This also goes to DefaultEngine.ini .

Starting from Engine version 4.25 also put

Another voice related variables worth playing with

To find available settings type voice. in editor console, and autocompletion widget will pop up.

Console variables can be modified in runtime like this

To debug your microphone input you can convert output sound buffer to unreal sound wave and play it.

Above values may differ depending on actual microphone characteristics.

• Go to google cloud and create payment account.
• Enable Cloud Speech-to-Text API and Cloud Text-to-Speech API .
• Create credentials to access your enabled APIs. See instructions here .

There are two ways how you can use your credentials in project.

4.1 By using environment variables. Create environment variable GOOGLE_API_KEY with created key as value.

4.2 By assigning key directly in blueprints. This can be called anywhere.

By default you need to set api key from nodes. To use environment variable, you need to set Use Env Variable to true .

ADVICE : Pay attention to security and encrypt your assets before packaging.

You need to supply text to async node, as well as voice variant, speech speed, pitch value and optionally audio effects. As output you will get sound wave object which can be played by engine.

Speech recognition

Consists of two parts. Voice capture, and sending request. There are two ways how you can capture your voice, depending on your needs.

Grant permissions

No actions needed

• In Xcode, select you project
• Go to Info tab
• Expand Custom macOS Application Target Properties section

Call this somewhere on begin play

Use provided MicrophoneCapture actor component as shown below. Next, construct recognition parameters and pass them to Google STT async node.

Cross platform method (use this instead)

Create SoundMix.

• Right click in content browser - Sounds > Mix > Sound Soundmix

Create sound class

• Right click in content browser - Sounds > Classes > Sound Class
• Open it, and set our submix that we created in previous step as sound class default submix

Go to your actor, and add AudioCapture component in components tab

Disable "Auto Activate" option on AudioCapture

Now we can drop some nodes. In order to start and stop recording, we use Activate and Deactivate nodes with previously added AudioCapture component as a target. When audio capture is activated, we can start recording output to our submix

Here is the whole setup

There is another STT node - Google STT Variants node. Which, instead of returning result with highest confidence, returns an array of variants.

Probably, you will need to process recognised voice in your app, to increase recognition chances use CompareStrings node. Below call will return 0.666 value, so we can treat those strings equal since they are simmilar on 66%. Utilizes Levenstein distance algorithm

You can pass microphone name to microphone capture component. To get list of available microphones, use following setup

Windows , Mac and Android .

Migration guide

EGoogleTTSLanguage was removed. You need to pass voice name as string ( Voice name column).

WARNING : Since synthesys parameters has changed, TTS cache is no longer valid! Make sure you remove TTS cache if exists. Editor/Game can freeze if old cache wll be loaded. So make sure to remove PROJECT_ROOT/Saved/GoogleTTSCache folder. Or invoke WipeTTSCache node before GoogleTTS node is executed!

The reason for this is that the number of languages has exceeded 256, and we can't put this amount into 8 bit enums (This is Unreal's limitation)

• Supported TTS voices ( WaveNet are the best)
• Speech synthesis config
• Supported STT languages
• Speech recognition config

Do-it-yourself artificial intelligence

With our maker kits, build intelligent systems that see, speak, and understand. Then start tinkering. Take things apart, make things better. See what problems you can solve.

Do-it-yourself intelligent camera. Experiment with image recognition using neural networks.

Build an intelligent camera that can see faces, detect emotions, and recognize common objects. Create your own projects that take action based on what the Vision Kit sees.

Do-it-yourself intelligent speaker. Experiment with voice recognition and the Google Assistant.

With the Google Assistant built-in, build an intelligent speaker that can understand you, and respond when you ask it a question or tell it to do something. Create your own projects that use voice recognition to control robots, music, games, and more.

Take a tour through the AIY Vision Kit with James, AIY Projects engineer, as he shows off some cool applications of the kit like the Joy Detector and object classifier.

Watch as James, AIY Projects engineer, talks about extending the AIY Voice Kit while building a voice-controlled model train.

• Español – América Latina
• Português – Brasil
• Cloud Speech-to-Text
• Documentation

Speech-to-Text documentation

Speech-to-Text enables easy integration of Google speech recognition technologies into developer applications. Send audio and receive a text transcription from the Speech-to-Text API service. Learn more

Documentation resources

Quickstart: Transcribe speech to text by using client libraries

Quickstart: Transcribe speech to text by using the API

Quickstart: Transcribe speech to text by using the gcloud CLI

Language support

Transcribing audio from streaming input

Transcribing long audio files

Speech-to-Text Client Libraries

Transcribing short audio files

Separating different speakers in an audio recording

Supported class tokens

Client libraries

Quotas & limits

Error messages

Release notes

Troubleshooting

Getting support

Billing questions

Related videos

Try speech-to-text for yourself.

Create an account to evaluate how our products perform in real-world scenarios. New customers also get $300 in free credits to run, test, and deploy workloads.

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License , and code samples are licensed under the Apache 2.0 License . For details, see the Google Developers Site Policies . Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2024-10-30 UTC.