• Supported service: llm
  • Key: openai_realtime
  • Integrated: No. See BYO Keys for more info.

​
Service options

​
model
string
default:
"gpt-4o-realtime-preview-2024-12-17"

The model that will complete your prompt. See the available OpenAI Realtime models here.

{
  "service_options": {
    "openai": {
      "model": "gpt-4o-realtime-preview-2024-12-17"
    }
  }
}

​
Configuration options

​
voice
string
required

The voice you want your speech-to-speech service to use. Find the available voices in the OpenAI docs.

{
  "name": "voice",
  "value": "echo"
}
​
temperature
float
default:
"1.0"

What sampling temperature to use, between 0.6 and 1.2.

{
  "name": "temperature",
  "value": 0.8
}
​
max_response_output_tokens
integer

The maximum number of tokens that can be generated in the completion. Range: 1 to 4096.

{
  "name": "max_response_output_tokens",
  "value": 4096
}
​
turn_detection
object

Configuration for turn detection.

{
  "name": "turn_detection",
  "value": {
    "type": "server_vad",
    "threshold": 0.5,
    "prefix_padding_ms": 300,
    "silence_duration_ms": 200
  }
}