Configuration Reference

This page documents every option available in each configuration section of the Voice Agent settings form. See The Voice Agent Editor for an overview of the form layout and how to navigate between sections.

Speech-to-Text (STT) Providers

Select the STT provider using the Transcriber dropdown at the top of the Input Speech Details section. Fields update automatically based on the selected provider.

Whisper

Self-hosted transcription using a Whisper model served via Ray Serve.

Field	Description
Default Language	Primary transcription language. Options: English, Vietnamese, Indonesian, Thai, Mandarin Chinese, Malay, Tamil, Telugu, Tagalog.
Candidate Languages	Additional languages the transcriber may switch to mid-call. Multi-select.
Whisper Ray URL	URL of the Ray Serve endpoint hosting the Whisper model. Required.

Advanced Settings (toggle to expand):

Field	Description
Chunk Duration (ms)	Length of each audio chunk sent for transcription. Default: 100.
Chunk Sleep	Sleep interval between chunk processing iterations (seconds). Default: 0.1.
Silence Threshold	Energy level below which audio is treated as silence (0–1). Default: 0.8.
Buffer Context	Number of previous chunks retained as context for the current transcription. Default: 2.
Beam Size	Beam search width for Whisper decoding. Higher values increase accuracy at the cost of latency. Default: 7.
VAD Min Silence Duration (ms)	Minimum duration of silence before the Voice Activity Detector (VAD) considers a speech segment complete. Default: 500.
Enable Denoiser	Apply audio denoising before transcription. Off by default.
Debug Mode	Log extended transcription diagnostics. Off by default.

Custom Transcriber

Field	Description
Default Language	Primary transcription language (BCP-47 code, e.g. `en-US`).
Candidate Languages	Additional languages for multi-language detection. Multi-select.
Speech Key	Azure Cognitive Services subscription key.
Speech Region	Azure region for the Speech service (e.g. `eastus`).
Use External VAD	Use an external Voice Activity Detector instead of Azure’s built-in VAD. Off by default.
VAD Silence Threshold	Duration of silence (seconds) before the external VAD ends a speech segment. Default: 1. Only visible when Use External VAD is on.
VAD Sample Rate	Audio sample rate (Hz) for the external VAD. Default: 16000. Only visible when Use External VAD is on.

AWS Transcriber

Amazon Transcribe streaming transcription.

Field	Description
Auto Language Identification	Let Amazon Transcribe detect the spoken language automatically. On by default.
Language	Fixed transcription language. Only visible when Auto Language Identification is off. Options span 26 languages including English (US/UK/AU/IN), Vietnamese, Thai, Indonesian, Malay, Tagalog, Tamil, Telugu, Hindi, Arabic, Japanese, Korean, Mandarin Chinese, and major European languages.
Preferred Language	The language to favour when multiple candidate languages are detected. Only visible when Auto Language Identification is on. Default: English (US).
Candidate Languages	Languages the identifier may choose between. At least 2 required when Auto Language Identification is on.
Use External VAD	Use an external Voice Activity Detector. Off by default.
VAD Silence Threshold	Duration of silence (seconds) before the external VAD ends a speech segment. Default: 0.5.
VAD Sample Rate	Audio sample rate (Hz) for the external VAD. Default: 16000.
Enable Denoiser	Apply audio denoising before transcription. Off by default.
Denoiser Type	Denoising algorithm to use. Options: `RNNoise`, `Other`. Only visible when Enable Denoiser is on.

Deepgram

Deepgram real-time streaming transcription API.

Field	Description
API Key	Deepgram API key. Required when On-Premise is off.
Language	Transcription language (BCP-47 code). Default: `en-US`.
Model	Deepgram model to use. For English, select `nova-2`. For Indonesian (`id-ID`), Vietnamese (`vi-VN`), or Malay (`ms-MY`), select a language-specific model version from the dropdown.
Model Version	Version string for the selected model.
WebSocket URL	Deepgram streaming endpoint URL. Leave empty to use Deepgram’s default cloud endpoint.
On-Premise	Connect to a self-hosted Deepgram instance via the WebSocket URL instead of Deepgram’s cloud. On by default.

ElevenLabs (STT)

ElevenLabs real-time speech-to-text using the scribe_v2_realtime model.

Field	Description
API Key	ElevenLabs API key. Required.
Model	ElevenLabs STT model. Default: `scribe_v2_realtime`.
Auto Language Detection	Detect the spoken language automatically. On by default.
Language	Fixed transcription language. Only visible when Auto Language Detection is off. Supports 28 languages including English, Spanish, French, German, Italian, Portuguese, Mandarin Chinese, Cantonese, Japanese, Korean, Vietnamese, Thai, Indonesian, Malay, Filipino, Arabic, Hindi, Tamil, Telugu, Kannada, Malayalam, Javanese, Cebuano, Khmer, Lao, Burmese, Afrikaans, and Swahili.
WebSocket URL	ElevenLabs STT streaming endpoint. Default: `wss://api.elevenlabs.io/v1/speech-to-text/realtime`.

Advanced Settings (toggle to expand):

Field	Description
VAD Silence Threshold (secs)	Duration of silence before the VAD ends a speech segment. Default: 0.5.
VAD Threshold	Sensitivity of the Voice Activity Detector (0–1). Default: 0.4.
Min Speech Duration (ms)	Minimum audio length to be treated as a speech event. Default: 150.
Min Silence Duration (ms)	Minimum silence length to be treated as end-of-turn. Default: 100.

Text-to-Speech (TTS) Providers

Select the TTS provider using the Synthesizer dropdown at the top of the Output Speech Details section.

ElevenLabs (TTS)

ElevenLabs high-quality voice synthesis.

Field	Description
API Key	ElevenLabs API key. Required.
Collection ID (Optional)	ElevenLabs voice collection ID. When provided, the Voice ID field becomes a dropdown listing voices from that collection.
Voice ID	ElevenLabs voice identifier. Entered as free text when no collection is specified; shown as a dropdown when a collection ID is set. Required.
Model	ElevenLabs TTS model. Options: Eleven v3, Eleven Flash v2.5, Eleven Flash v2, Eleven Turbo v2.5, Eleven Turbo v2, Eleven Multilingual v2, Eleven Multilingual v1, Eleven English STS v2, Eleven English STS v1. Required.
Preview	Play/pause button to audition the selected voice before saving.

Advanced Settings (toggle to expand):

Field	Description
Stability	Voice consistency slider (0–1). Higher values produce more consistent output; lower values allow more expressive variation. Default: 0.82.
Speed	Speech rate (0.7–1.2). Default: 1.0.
Style	Stylistic intensity of the voice (0–1). Default: 0.
Similarity Boost	How closely the synthesis adheres to the original voice sample (0–1). Default: 0.81.
Optimize Streaming Latency	Latency optimisation level (integer). Higher values reduce latency at the cost of some quality. Default: 3.
Use Speaker Boost	Apply speaker boost enhancement. On by default.
Experimental Streaming	Enable experimental streaming mode for lower latency. On by default.
Experimental WebSocket	Use an experimental WebSocket connection for streaming. On by default.

AWS Polly

Amazon Polly neural and standard voice synthesis.

Field	Description
Language	Language for voice selection. Options: English (US/UK/AU/IN), Spanish (US/Spain), French (France), German, Italian, Japanese, Korean, Portuguese (Brazil), Mandarin Chinese, Hindi, Arabic (Gulf).
Engine	Synthesis engine: Neural (Recommended) or Standard.
Voice	Available voices are loaded dynamically based on the selected language. Each option shows the voice name and gender. Required.
Preview	Play/pause button to audition the selected Polly voice.

Language Model (LLM) Providers

Select the LLM provider using the LLM Provider dropdown at the top of the Language Model Configuration section.

Bedrock

Field	Description
Client Type	AWS SDK client to use: Boto3 (default) or Langchain.
AWS Region	AWS region for the Bedrock service (e.g. `us-east-1`). Default: `us-east-1`.
Endpoint URL (Optional)	Custom endpoint URL for private or on-premise deployments.
Model Provider	The model provider name (e.g. `amazon`, `anthropic`). Default: `amazon`.
Model ID	The Bedrock model identifier. Default: `us.amazon.nova-pro-v1:0`.
Temperature	Sampling temperature (0–2). Default: 0.3.
Max Tokens	Maximum tokens in the model’s response (1–10000). Default: 3000.
Enable Streaming	Stream the model response token-by-token for lower perceived latency. On by default.

Custom LLM1

Field	Description
API Key	API key for the endpoint.
Model	Model identifier. Options: Custom Model1, Custom Model2.
Temperature	Sampling temperature (0–2). Default: 0.
Max Tokens	Maximum tokens in the response (1–32000). Default: 1024.
Enable Streaming	Stream the model response. On by default.

Custom LLM2

Field	Description
API Key	API key for the endpoint.
Endpoint	Resource endpoint URL.
Deployment	Deployment name (e.g. `gpt-4o`).
Model Name	Model name for the deployment (e.g. `gpt-4o`).
API Version	API version string. Default: `2024-02-15-preview`.
Temperature	Sampling temperature (0–2). Default: 0.3.
Max Tokens	Maximum tokens in the response (1–32000). Default: 1024.
Enable Streaming	Stream the model response. On by default.

Phone Configuration Reference

See The Voice Agent Editor for the full Phone Configuration field list. Key parameters to note:

Auth Token vs API Keys — you must provide either an Auth Token, or both API Key SID and API Key Secret. Providing both sets is also valid.
Status Callback Events — any combination of Initiated, Ringing, Answered, Completed can be subscribed to independently.
Extra Parameters — arbitrary Twilio TwiML parameters can be passed as key/value pairs. Common examples include region (e.g. us1) and edge (e.g. sydney) for Twilio Global Low Latency routing.

Call Termination Reference

Terminate Call on Keyword — off by default. When enabled, the agent monitors transcribed speech for any of the configured keywords and hangs up the call when a match is detected.
Termination Keywords — entered as a comma-separated string (e.g. goodbye, bye, end call). Case-insensitive matching.