im currently using the follow set up in my deepgram exploration (see below) . I found that when deepgram is readout the single words with comma such as (apple, orange, peach, etc) there is no "pause" between the words, it read/speak through it just like there are no comma in between. is there a way or setting I can tweek to allow the agent to have a bit more clear flow in reading through a sentence when the sentence has punctuations?
deepgram_config = {
"type": "Settings",
"audio": {
"input": {
"encoding": "mulaw",
"sample_rate": 8000,
},
"output": {
"encoding": "mulaw",
"sample_rate": 8000,
"container": "none", # This field is valid for V1
}
},
"agent": {
"listen": {
"provider": {
"type": "deepgram"
}
},
"think": {
"provider": {
"type": "open_ai",
"model": "gpt-4o-mini"
},
"prompt": enhanced_system_message, # Changed from "instructions" to "prompt" per V1 guide
"functions": all_english_function_definitions
},
"speak": {
"provider": {
"type": "deepgram",
"model": "aura-asteria-en"
}
}
}
}