Ai Parameters
Appendix
Reference materials, patterns, best practices, and troubleshooting guides for the SignalWire Agents SDK.
About This Chapter
This appendix provides supplementary reference materials to support your development with the SignalWire Agents SDK.
Quick Reference
Chapter Contents
Overview
Setting Parameters in Python
LLM API Parameters
These parameters control the AI model’s behavior. Set in prompt or post_prompt sections.
Temperature
Controls randomness in output generation:
- 0.0: Deterministic, consistent responses
- 0.3 (default): Balanced creativity
- 1.0+: More creative, less predictable
Reasoning Effort
For o1-style models only:
"low": Quick responses"medium": Balanced reasoning"high": Deep analysis
ASR (Speech Recognition) Parameters
Control automatic speech recognition behavior.
Timing Parameters
Control various timeouts and timing behaviors.
Key Timeouts
- end_of_speech_timeout: Milliseconds of silence to detect end of speech
- attention_timeout: How long to wait before prompting user (0 disables)
- inactivity_timeout: How long before auto-hangup (default 10 minutes)
Hard Stop Time
Behavior Parameters
Control various AI agent behaviors.
SWAIG Control Parameters
Interrupt Parameters
Debug Parameters
Audio Parameters
Hold Music with Tone
Video Parameters
String Parameters
VAD Configuration
Voice Activity Detection uses a string format: silero_thresh:frame_ms
Post-Prompt Parameter Defaults
Parameters have different defaults in post_prompt for more deterministic summaries:
Model-Specific Overrides
Different models support different parameters: