Skip to main content

Usage guide

Setup, environment variables, and Python/JavaScript/Go usage examples.

​
UltravoxRealtime

Realtime speech-to-speech integration for Ultravox. Wraps an Ultravox model so it can be used as a full speech-to-speech provider within the runtime. Configuration is supplied through an UltravoxLiveConfig instance and resolved into a flat parameter map for the runtime.

​
Constructor

​
api_key
str | None
Ultravox API key. When omitted, the value of the ULTRAVOX_API_KEY environment variable is used.
​
config
UltravoxLiveConfig | None
Provider configuration. When omitted, a default UltravoxLiveConfig is used.

​
aclose

Release any resources held by the integration. This implementation performs no work and exists so the integration can be used interchangeably with providers that require teardown.

​
cleanup

Clean up the integration by delegating to aclose.

​
UltravoxLiveConfig

​
Fields

​
model
str
default:"fixie-ai/ultravox"
​
voice
Optional[str]
​
language_hint
str
default:"en"
​
temperature
Optional[float]
​
max_duration
Optional[str]
​
time_exceeded_message
Optional[str]
​
input_sample_rate
int
default:"48000"
​
output_sample_rate
int
default:"24000"
​
client_buffer_size_ms
int
default:"30000"
​
vad_turn_endpoint_delay_ms
Optional[int]
default:"800"
​
vad_minimum_turn_duration_ms
Optional[int]
default:"600"
​
vad_minimum_interruption_duration_ms
Optional[int]
​
vad_frame_activation_threshold
Optional[float]
default:"0.4"
​
first_speaker
Optional[str]
default:"FIRST_SPEAKER_USER"
​
enable_greeting_prompt
bool
default:"False"
​
base_url
Optional[str]