Stack Overflow
Stack Overflow

Questions tagged [google-cloud-speech]

Google Cloud Speech API enables developers to convert audio to text by applying powerful neural network models in an easy to use API

Google Cloud Speech API enables developers to convert audio to text by applying powerful neural network models in an easy to use API.

  • The API recognizes over 80 languages and variants, to support your global user base. You can transcribe the text of users dictating to an application’s microphone, enable command-and-control through voice, or transcribe audio files, among many other use cases.
  • Recognize audio uploaded in the request, and integrate with your audio storage on Google Cloud Storage, by using the same technology Google uses to power its own products.

try it

534 questions
46
votes
10 answers

ImportError: No module named google.cloud

I am unable to import google.cloud.speech from google.cloud import speech I have installed it using : pip install --upgrade google-cloud-speech -t dir-name It is giving me below error while importing it from dir-name ImportError: No module named…
nishith
  • 783
  • 1
  • 8
  • 17
38
votes
1 answer

Difference between Android Speech to Text API (Recognizer Intent) and Google Cloud Speech API?

So i'm looking into building a speech to text app for fun. I did some research and found an inbuilt Speech to Text API using RecognizerIntent that is free, but also found that google is now offerieng a cloud speech API that the charge for. My…
AndroidDev21921
  • 645
  • 1
  • 7
  • 19
34
votes
1 answer

Unable to get results from Google text to speech api while streaming audio from web

I want to stream audio from the web and convert that to text using Python Google-cloud-speech API. I have integrated that in my Django channels code. For frontend, I have directly copied this code and the backend has this code (please see below).…
Lokesh Sanapalli
  • 936
  • 2
  • 15
  • 38
19
votes
3 answers

How can I extract the preceding audio (from microphone) as a buffer when silence is detected (JS)?

I'm using the Google Cloud API for Speech-to-text, with a NodeJS back-end. The app needs to be able to listen for voice commands, and transmit them to the back-end as a buffer. For this, I need to send the buffer of the preceding audio when silence…
azhar
  • 1,591
  • 1
  • 16
  • 36
16
votes
3 answers

Google Speech Recognition API Result is Empty

I'm performing an asynchronous request to Google Cloud Speech API, and I do not know how to get the result of operation: Request POST: https://speech.googleapis.com/v1beta1/speech:asyncrecognize Body: { "config":{ "languageCode"…
Bruno
  • 418
  • 5
  • 13
14
votes
1 answer

How to get SSML timestamps from Google Cloud text-to-speech API

I want to use SSML markers through the Google Cloud text-to-speech API to request the timing of these markers in the audio stream. These timestamps are necessary in order to provide cues for effects, word/section highlighting and feedback to the…
James
  • 141
  • 4
13
votes
2 answers

User data privacy in Google speech to text api / Google cloud speech solution

What level of data privacy is maintained when I used Google speech to text api or google cloud speech solution. I want to know this because I am working on an application which converts audio files into text and those files may contain user…
Bhargav Deshpande
  • 131
  • 1
  • 3
12
votes
1 answer

How do I stream live audio from the browser to Google Cloud Speech via socket.io?

I have a situation with a React-based app where I have an input for which I wanted to allow voice input as well. I'm okay making this compatible with Chrome and Firefox only, so I was thinking of using getUserMedia. I know I'll be using Google…
Amber B.
  • 904
  • 6
  • 19
11
votes
2 answers

Google Speech-to-text API, InvalidArgument: 400 Must use single channel (mono)

I keep getting this error InvalidArgument: 400 in google Speech-to-text, and the problem seems to be that I an using a 2 channel audio(Stereo), and the API is waiting for a wav in (Mono). If I convert the file in a audio editor it might work, but I…
Jose silvestre Rodriguez Ortiz
  • 121
  • 1
  • 4
10
votes
3 answers

Is there a way to generate an SRT file (or similar) using Google Cloud Speech?

In order to generate subtitles for my videos, I converted them to audio files and used the Cloud Speech-to-Text. It works, but it only generates transcriptions, whereas what I need is a *.srt/*.vtt/similar file. What I need is what YouTube does: to…
Lucas Caton
  • 2,382
  • 1
  • 19
  • 31
9
votes
2 answers

Cannot import com.google.cloud.speech.v1.SpeechGrpc in Android

I'm trying to use Google's Speech API in Android project. The example project works. I'm having trouble to use it in my own android app. build.gradle(Module:app) : apply plugin: 'com.android.application' apply plugin: 'com.google.protobuf' ext { …
tezz
  • 311
  • 2
  • 15
8
votes
3 answers

How to end Google Speech-to-Text streamingRecognize gracefully and get back the pending text results?

I'd like to be able to end a Google speech-to-text stream (created with streamingRecognize), and get back the pending SR (speech recognition) results. In a nutshell, the relevant Node.js code: // create SR stream const stream =…
noseratio
  • 56,401
  • 21
  • 172
  • 421
8
votes
1 answer

How to receive long running operation results via Google Cloud Pub/Sub API

When long running operations are kicked off in Google Cloud APIs, the service might return an object with an "Operations" shape. The status of the operation can then be polled through this object and the results obtained when complete. I'd like to…
ximus
  • 267
  • 2
  • 10
7
votes
1 answer

Need help Speech-to-text, always failed for too many retries

I use google speech-to-text API to get subtitles from audio, but when audio is too long, normally longer than 60 minutes, it will fail for too many retries.It says: google.api_core.exceptions.GoogleAPICallError: None Too many retries, giving up. Can…
DLI42
  • 79
  • 1
7
votes
1 answer

Google cloud speech API not transcription from base64 audio

I'm trying to use Google cloud speech API, by recording audio in my Angular FrontEnd, converting it to base64, sending it to my Node backend, which does the query to google speech API. So far I have had no success with it, google only sending me…
Oumpaloumpa
  • 123
  • 1
  • 7
1
2 3
…
35 36