# Asterisk Audio Stream **URL:** \ **Category:** Asterisk Support\ **Created:** [March 5, 2024, 3:21pm UTC](https://community.asterisk.org/t/asterisk-audio-stream/101343 "2024-03-05T15:21:50Z")\ **Posts on this page:** 7\ **Page:** 1
**Author:** ![AfnanMalik](https://avatars.discourse-cdn.com/v4/letter/a/6de8d8/32.png) [@AfnanMalik](https://community.asterisk.org/u/AfnanMalik)\ **Post date:** [March 5, 2024, 3:21pm UTC](https://community.asterisk.org/t/asterisk-audio-stream/101343/1 "2024-03-05T15:21:50Z")
I want to get the audio from call without saving it in audio file and use for Speech to text. for example: i want to record Bob response direct from call to and convert it into text and then converted text will be use for further processing ---
**Author:** ![jsonchan000](https://sea1.discourse-cdn.com/asterisk/user_avatar/community.asterisk.org/jsonchan000/32/6979_2.png) [@jsonchan000](https://community.asterisk.org/u/jsonchan000)\ **Post date:** [March 6, 2024, 3:29am UTC](https://community.asterisk.org/t/asterisk-audio-stream/101343/2 "2024-03-06T03:29:50Z")
[asterisk/asterisk-external-media (github.com)](https://github.com/asterisk/asterisk-external-media) This project stream audio to a rtp server and send the raw data to google STT. ---
**Author:** ![danishhafeez](https://avatars.discourse-cdn.com/v4/letter/d/977dab/32.png) [@danishhafeez](https://community.asterisk.org/u/danishhafeez)\ **Post date:** [March 6, 2024, 5:43am UTC](https://community.asterisk.org/t/asterisk-audio-stream/101343/3 "2024-03-06T05:43:17Z")
> [@AfnanMalik](#): > > I want to get the audio from call without saving it in audio file and use for Speech to text. > for example: > i want to record Bob response direct from call to and convert it into text and then converted text will be use for further processing To achieve this, you would typically use a technique known as real-time speech recognition or live transcription. here’s a short example in Python using the Google Cloud Speech-to-Text API and the Twilio API for call handling: ```auto import os from twilio.rest import Client from google.cloud import speech_v1p1beta1 as speech # Twilio credentials TWILIO_ACCOUNT_SID = 'your_twilio_account_sid' TWILIO_AUTH_TOKEN = 'your_twilio_auth_token' TWILIO_PHONE_NUMBER = 'your_twilio_phone_number' # Google Cloud credentials os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = "path_to_your_google_credentials.json" # Initialize Twilio client client = Client(TWILIO_ACCOUNT_SID, TWILIO_AUTH_TOKEN) # Function to transcribe call def transcribe_call(call_sid): call = client.calls(call_sid).fetch() audio_url = call.recordings.list()[0].uri # Initialize Google Speech-to-Text client speech_client = speech.SpeechClient() # Configure audio settings audio = speech.RecognitionAudio(uri=audio_url) config = speech.RecognitionConfig( encoding=speech.RecognitionConfig.AudioEncoding.LINEAR16, sample_rate_hertz=8000, language_code="en-US", ) # Perform transcription response = speech_client.recognize(config=config, audio=audio) # Print transcription for result in response.results: print("Transcript: {}".format(result.alternatives[0].transcript)) # Example usage call_sid = 'your_call_sid' transcribe_call(call_sid) This code assumes you have a call SID from Twilio that you want to transcribe. It uses the Twilio Python library to fetch the call recording URL, then uses the Google Cloud Speech-to-Text API to transcribe the audio from the recording URL into text. Finally, it prints the transcription. You'll need to replace 'your_twilio_account_sid', 'your_twilio_auth_token', 'your_twilio_phone_number', 'path_to_your_google_credentials.json', and 'your_call_sid' with your actual Twilio and Google Cloud credentials and the specific call SID you want to transcribe. Best regard Danish Hafeez | QA Assistant [ICTInnovations](https://www.ictinnovations.com) ``` ---
**Author:** ![AfnanMalik](https://avatars.discourse-cdn.com/v4/letter/a/6de8d8/32.png) [@AfnanMalik](https://community.asterisk.org/u/AfnanMalik)\ **Post date:** [March 6, 2024, 6:55am UTC](https://community.asterisk.org/t/asterisk-audio-stream/101343/4 "2024-03-06T06:55:23Z")
Is there any other way… like from dialplan or writing AGI. Actually i’m trying to get the audio in AGI … Recording audio stream in buffer and then pass it to STT. Or any dialplan application that can get audio stream store in buffer rather than saving auido in file by using record, monitor or mixmonitor ---
**Author:** ![danishhafeez](https://avatars.discourse-cdn.com/v4/letter/d/977dab/32.png) [@danishhafeez](https://community.asterisk.org/u/danishhafeez)\ **Post date:** [March 6, 2024, 7:07am UTC](https://community.asterisk.org/t/asterisk-audio-stream/101343/5 "2024-03-06T07:07:48Z")
Yes, you can capture audio in an Asterisk AGI script without saving it to a file by using a tool like `sox` or `arecord` to capture the audio stream and then passing it to your speech-to-text (STT) engine. ```auto #!/usr/bin/env python3 import os import subprocess def capture_audio(duration): # Using arecord to capture audio for the specified duration process = subprocess.Popen(["arecord", "-d", str(duration), "-f", "S16_LE", "-r", "16000", "-c", "1", "-t", "raw"], stdout=subprocess.PIPE) audio_data, _ = process.communicate() return audio_data def main(): # Define the duration for capturing audio (in seconds) duration = 5 # Capture audio audio_data = capture_audio(duration) # Pass the captured audio to your STT engine for processing # Replace this line with your code to send the audio data to your STT engine if __name__ == " __main__": main() You can call this AGI script from your dialplan to capture audio and then process it with your STT engine. Make sure that the necessary permissions are set for executing the AGI script and capturing audio. Additionally, you may need to install the sox or arecord package if it's not already installed on your system. ``` ---
**Author:** ![AfnanMalik](https://avatars.discourse-cdn.com/v4/letter/a/6de8d8/32.png) [@AfnanMalik](https://community.asterisk.org/u/AfnanMalik)\ **Post date:** [March 6, 2024, 7:54am UTC](https://community.asterisk.org/t/asterisk-audio-stream/101343/6 "2024-03-06T07:54:11Z")
i’m using azure and asterisk is deployed on vm ALSA lib confmisc.c:767:(parse\_card) cannot find card ‘0’ ALSA lib conf.c:4745:(\_snd\_config\_evaluate) function snd\_func\_card\_driver returned error: No such file or directory ALSA lib confmisc.c:392:(snd\_func\_concat) error evaluating strings ALSA lib conf.c:4745:(\_snd\_config\_evaluate) function snd\_func\_concat returned error: No such file or directory ALSA lib confmisc.c:1246:(snd\_func\_refer) error evaluating name ALSA lib conf.c:4745:(\_snd\_config\_evaluate) function snd\_func\_refer returned error: No such file or directory ALSA lib conf.c:5233:(snd\_config\_expand) Evaluate error: No such file or directory ALSA lib pcm.c:2660:(snd\_pcm\_open\_noupdate) Unknown PCM default arecord: main:830: audio open error: No such file or directory ---
**Author:** ![system](https://global.discourse-cdn.com/asterisk/original/2X/4/475d0c889911cfb84ac4881ad6df8b523e3f9105.png) [@system](https://community.asterisk.org/u/system)\ **Post date:** [April 5, 2024, 7:54am UTC](https://community.asterisk.org/t/asterisk-audio-stream/101343/7 "2024-04-05T07:54:53Z")
This topic was automatically closed 30 days after the last reply. New replies are no longer allowed.