Documentation Index
Fetch the complete documentation index at: https://docs.opendot.ai/llms.txt
Use this file to discover all available pages before exploring further.
Configuration is the second page in the console workflow. It takes the selected
draft agent from Agent Studio and turns it into an explicit voice runtime
configuration.
The page is intentionally organized around the same four pipeline stages that
the runtime executes:
What you see in the UI
Each stage card has the same shape:
- stage number and icon
- stage label and purpose
- provider name
- model selector
- stage settings
- emitted runtime events
If no agent is selected, Configuration shows an empty state. Create or select an
agent in Agent Studio first.
Stage 1: Voice activity
| Field | Default | Purpose |
|---|
| Provider | Deepgram | Uses Deepgram live listen options for turn detection. |
| Model | endpointing-vad | Keeps VAD visible as a product stage. |
| Endpointing | 900 ms | Controls how quickly silence closes a turn. |
| Utterance end | 1000 ms | Adds a safer pause for device conversations. |
| Turn events | vad_events, interim_results, speech_final | Enables runtime feedback and turn close events. |
| Noise floor | 2 characters | Ignores tiny transcript fragments. |
| Return device to wake word | enabled | Lets firmware leave active listening after a completed turn. |
Stage 2: Speech to text
| Field | Default | Purpose |
|---|
| Provider | Deepgram | Streams microphone or device audio to STT. |
| Model | nova-3 | Default live transcription model. |
| Language | en-US | Recognition language. |
| Encoding | linear16 | Browser runtime audio format. |
| Sample rate | 16000 | Input sample rate sent to the runtime. |
| Features | smart_format | Transcript formatting options. |
Stage 3: Language model
| Field | Default | Purpose |
|---|
| Provider | OpenAI | OpenAI-compatible response generation. |
| Model | gpt-5.4-mini | Default starter model. |
| API | Responses API | Streaming text generation path. |
| System prompt and chunk rules | voice assistant prompt plus chunk instructions | Shapes the assistant response and TTS chunking. |
| Reasoning effort | configurable | Controls model reasoning behavior where supported. |
| Verbosity | configurable | Controls response density where supported. |
<chunk>First spoken phrase.</chunk><chunk>Next spoken phrase.</chunk>
Stage 4: Text to speech
| Field | Default | Purpose |
|---|
| Provider | Deepgram | Synthesizes assistant text into audio. |
| Model | aura-2-thalia-en | Default starter voice. |
| Encoding | mp3 | Output audio encoding. |
| Sample rate | 24000 | Runtime TTS sample rate. |
| Browser delivery | chunked audio files | Browser playback mode. |
| Chunk style | fast phrases | Controls how short streamed TTS chunks should be. |
Linear16 PCM with Direct PCM stream when you want raw PCM playback in
the browser. Other encodings are retained as chunked audio files for playback.
What gets persisted
Changing Configuration updates the selected agent through the platform API. The
API writes a new draft agent version and a new draft pipeline version in
PostgreSQL. The runtime later loads the authorized version when Browser Test
opens a voice session or a Dot device connects with valid credentials.
See Platform architecture for the full system boundary and
Browser Test for the next step in the UI workflow.
