Model and Voice Settings
How to choose models and voices for Voice Agent in Standard and Realtime modes.
Overview
Users can choose personal model and voice preferences in Web App > avatar > Settings > Voice. If a field is left as Default, Assistant Core uses the default model for the user's current plan.
Each plan has a different list of available models. See AI Models for the model catalog, voice lists, and default models.
The Language model (LLM) in Standard mode is used only for voice turns. It does not change the Chat model in the Web App header. See Chat Model Selection if you want to change the model for text chat.
Admins enable voice, recording policy, and Stream Response Text in the Admin Panel. See Enable Voice.
Standard Mode
Standard mode runs a chained pipeline: listen to speech → transcribe to text → generate the AI answer → read the answer aloud with TTS.
| Setting | Role | How to choose |
|---|---|---|
| Voice activity detection (VAD) model | Detects when the user starts and stops speaking | Keep Default unless you need to tune turn-ending behavior |
| Speech recognition (ASR) model | Transcribes speech to text | Choose a stronger model if transcripts are often wrong, especially for Vietnamese, accents, or noisy environments |
| Language model (LLM) | Generates the answer | Use a fast/cost-effective model for normal Q&A; choose a stronger model for reasoning, tool use, or long questions |
| Text-to-speech (TTS) model | Converts the answer into spoken audio | Choose based on voice quality, latency, language support, and credit cost |
| Voice | The spoken persona for Standard mode | Select this after choosing the TTS model; available voices depend on that model |
| Speech speed | How fast TTS audio is spoken | Slow it down for careful listening; speed it up for quick operational use |
| Silence duration | How long to wait before ending the user's turn | Increase it if users pause often; decrease it for faster responses |
Realtime Mode
Realtime mode uses a native voice model to process live audio directly with very low turn latency. Because of that, Realtime has its own model and voice selection. Realtime does not use the Standard-mode TTS voice.
| Setting | Role | How to choose |
|---|---|---|
| Realtime model | Handles native live voice conversation | Choose a low-latency model for natural conversation; choose a stronger model when instruction following or tool use is more complex |
| Realtime voice | Native voice for the selected Realtime model | Select this after choosing the Realtime model; changing models may reset the voice because each model has its own voice list |
If the Realtime section does not appear, the current plan does not include Realtime models. See Plans & Pricing for plan availability.
Credit Cost
Voice usage consumes credits based on the model and usage:
| Type | How it is charged |
|---|---|
| ASR | By audio duration |
| TTS | By character count or audio duration, depending on provider |
| Realtime Voice | By session duration |
See Credits & Usage to understand how credits are calculated.
If you are not sure what to choose, keep Default. Defaults are selected for your current plan and are usually balanced for quality, speed, and credits.