Updated doc renamed transcription to Voicegain SIP Media Stream B2BUA

freeswitch/transcription-proxy/README.md

@@ -1,7 +1,9 @@
 ![FSProxy](./FSProxy.png)
 
-# FreeSWITCH Transcription Proxy
-Proxy your SIP call via our FreeSWITCH docker and get the transcript of the call audio submitted to a websocket service.
+# Voicegain SIP Media Stream B2BUA
+Voicegain offers a highly scalable, reliable and fully contained SIP Media Stream B2BUA to address the challenge discussed above. This B2BUA is a containerized network element that is deployed in the same network as the premise-based contact center. From a SIP Protocol standpoint, this Media Stream Back-to-Back User Agent (B2BUA)  acts as a transparent media relay while forking SIP RTP media streams to real-time Speech-to-Text..
+
+Please refer to this link for more information https://www.voicegain.ai/post/accessing-real-time-media-streams-generative-ai 
 
 ```Steps for setting up websocket service to receive transciption results in realtime```
 # 1) Install required python pacakges
@@ -38,9 +40,12 @@ python ws_server.py
 # 5) Modify config.ini for Freeswitch docker 
 A sample config.ini can be found in this repository.
 ```ini
-# This is the SIP proxy host where you will be sending SIP traffic to
+# This is the SIP B2BUA host where you will be sending SIP traffic to 
 FREESWITCH_HOST_DOMAIN=fs1lab.ascalon.ai
+# If this value is present then this IP used as SIP trunk to make outbound calls
+SIP_GATEWAY_IP=10.1.0.4:64793
 # This is the final SIP destination domain where will be proxying to.
+#if SIP_GATEWAY_IP is ip mentioned above then this below value will be ignored 
 DESTINATION_DOMAIN=fs.ascalon.ai:5080
 # this main voicegain API gateway URL 
 VG_GATEWAY_URL=https://api.voicegain.ai/v1/asr/transcribe/async
@@ -56,6 +61,10 @@ RIGHT_CHANNEL_NAME=CALLER2
 #words - words with confidence and timing info [also sent over websocket]
 #segments -- segments (or partial hypotheses) [also sent over websocket, note that latency of segments is higher than that of words by about 300-500ms]]
 CONTENT_INCREMENTAL=words
+DIALED_NUMBER_MAPPING=1233:4567
+SENSITIVITY=1
+AUDIO_CAPTURE=true
+NOAUDIOTIMEOUT=31000 
 ```
 # 6) Obtain FreeSWITCH proxy docker
 
@@ -71,15 +80,15 @@ With host networking:
 -v option specifies local file path where config.ini is located this needs to be changed to where the file was copied.
 -m to limit memory usage by freewitch docker so below example puts 1GB limit
 ```sh
-docker run -d --name fsproxy --network=host -m 1g -v /Path_to/config.ini:/etc/config.ini us-docker.pkg.dev/voicegain-prod/vg-customer-private/freeswitch-transcription-proxy:0.8.0
+docker run -d --name fsproxy --network=host -m 1g -v /Path_to/config.ini:/etc/config.ini us-docker.pkg.dev/voicegain-prod/vg-customer-private/freeswitch-transcription-proxy:0.14.6
 ```
 With bridge networking:
 ```sh
 -v option specifies local file path where config.ini is located this needs to be changed to where the file was copied.
-docker run -d --name fsproxy -p -p 5060:5060/tcp -p 5060:5060/udp -v /Path_to/config.ini:/etc/config.ini us-docker.pkg.dev/voicegain-prod/vg-customer-private/freeswitch-transcription-proxy:0.8.0
+docker run -d --name fsproxy -p -p 5060:5060/tcp -p 5060:5060/udp -v /Path_to/config.ini:/etc/config.ini us-docker.pkg.dev/voicegain-prod/vg-customer-private/freeswitch-transcription-proxy:0.14.6
 ```
 
-Note 1: Be cartefull with the path to the config.ini on Windows systems
+Note 1: Be carefull with the path to the config.ini on Windows systems
 
 Note 2: If you get an error mentioning `parseConfigFile` and `Is a directory` the most likely the path to config.ini was incorrectly provided
 

freeswitch/transcription-proxy/config.ini

@@ -7,3 +7,9 @@ WEBSOCKET_SERVER=wss://mydomain.com:8765
 LEFT_CHANNEL_NAME=CALLER1
 RIGHT_CHANNEL_NAME=CALLER2
 CONTENT_INCREMENTAL=words
+SIP_GATEWAY_IP=10.1.0.4:64793
+DIALED_NUMBER_MAPPING=1233:4567
+SENSITIVITY=1
+AUDIO_CAPTURE=true
+NOAUDIOTIMEOUT=31000 
+