Questions tagged [google-speech-api]

With Google Speech API you can convert speech to text file based or live stream

The https://cloud.google.com/speech/ and is part of https://cloud.google.com/products/ to allow for speech to text conversion.

When using a live stream words are returned almost realtime. This is limited by 1 minute or when paused for ~1 second. When using an asynchronous file the speech to text can be as long as 80 minutes. See https://cloud.google.com/speech/limits

For more see https://cloud.google.com/speech/docs/

837 questions
0
votes
3 answers

Convert .m4a to .wav

I need to convert buffer audio file .m4a to buffer audio file .wav for send to google speech api by NodeJS var toWav = require('audiobuffer-to-wav') var xhr = require('xhr') var context = new AudioContext() // request the MP3 as binary xhr({ …
otaroo
  • 83
  • 3
  • 10
0
votes
1 answer

How can i improve confidence of long_running_recognize in Google Speech API

I am currently developing a speech recognition service using the Google Speech API (Python). There is no sound other than the voice of the voice actor in the Korean listening evaluation mp3 file which is being used as the sample now. I am currently…
0
votes
0 answers

How can I relay a audio stream from browser to Google Speech API?

I am developing speech-to-text web application with Google Speech API, and stucked. Problem is, I do not understand how to relay audio stream from browser to Google Speech API. I want Google Speech API to convert audio stream to text on real time,…
blackawa
  • 1
  • 1
0
votes
1 answer

Google Speech Cloud error on Android: OUT_OF_RANGE: Exceeded maximum allowed stream duration of 65 seconds

First: I already know there is a 65 second limit on continuous speech recognition streaming with this API. My goal is NOT to extend those 65 seconds. My app: It uses Google's streaming Speech Recognition, I based my code on this example:…
Josh
  • 6,251
  • 2
  • 46
  • 73
0
votes
2 answers

Error in JSON payload while trying to access google cloud speech api

{ "config": { "encoding":"FLAC", "sample_rate": 16000, "language_code": "en-US" }, "audio": { "uri":"gs://speechtotextapi/audio_file.flac" } } curl -s -X POST -H "Content-Type: application/json" --data-binary…
Rajul
  • 71
  • 9
0
votes
1 answer

Google Speech application stops 3 seconds after start

I'm trying to run nodeJS Google Speech example, but when I start it with node recognize.js listen it stops after 3 seconds without any output. There is no error output. I've already tried other NodeJS programs and they run without problems. I'm…
Vitor F.M.
  • 119
  • 7
0
votes
0 answers

Google Speech Quota exceeded

I often receive following error when I call Google Speech API. This error has occurred from yesterday. ERROR: { [Error: Quota exceeded.] code: 8, metadata: Metadata { _internal_repr: {} }, note: 'Exception occurred in retry method that was not…
Tet
  • 1
0
votes
0 answers

While installing through pods, its not installing and getting error "[!] No podspec found for `googleapis` in `

I am doing Objective-C for iOS application and I want to install google cloud speech api, as per docs, Google docs given example in following link, I followed for…
0
votes
1 answer

Limitations of Google Speech API

Can someone share the limitation of google Speech API ? We heard below limitations so far: Can’t transcribe audio files more than 60 seconds Can’t handle dual channel (agent and customer) Thanks
Venkat
  • 1
  • 1
0
votes
1 answer

Google speech recognition api - bad request

I have an issue with google speech recognition API. I am making successful calls with the examples provided in the documentation. However, my input is in mp3 format (8 Khz). I suspect that the transformation to FLAC which I did with an online tool…
0
votes
0 answers

How to integrate Google Voice Recognition Engine on Offline

I'm going to use Google Voice Recognition on Android. I used SpeechRecognizer online, but it needs some time to get the result. So I'm hoping to use the engine offline and integrate into project. Is this possible?
0
votes
1 answer

Google SpeechClient service's authorisation does not recognise the environment variable set.

I have been trying to use the SpeechClient in one of my applications which is running on a remote debian machine.I have set the environment variable GOOGLE_APPLICATION_CREDENTIALS with the value of the path to the json key file(echo…
0
votes
1 answer

Speech Recognition Library in Python always returns same string

I'm trying to use Google Speech recognition, My problem is that after saying something into microphone, results are always same. My Function looks like this def RecordAudio(): import speech_recognition as sr r = sr.Recognizer() with…
Tornike Gomareli
  • 1,564
  • 2
  • 16
  • 28
0
votes
2 answers

Chrome web speech recognition api results returning repeated words?

I am trying the web speech recognition api for speech to text. There is an online demo here https://www.google.com/intl/en/chrome/demos/speech.html but if I try that or even implement it myself, there is a problem of it repeating words. So if I say…
omega
  • 40,311
  • 81
  • 251
  • 474
0
votes
1 answer

Instance created via Service Account unable to use Google Cloud Speech API - authentication error

I followed Google's Quick-Start documentation for the Speech API to enable billing and API for an account. This account has authorized a service account to create Compute instances on its behalf. After creating an instance on the child account,…
user1111380
  • 551
  • 2
  • 6
  • 17