Agents
Voice Configuration
Choose STT, TTS, and LLM providers for your agent's voice pipeline.
The Voice tab configures the three core services in your agent's pipeline.
Speech-to-Text (STT)
Converts the caller's speech into text for the LLM.
| Provider | Models | Languages | Notes |
|---|---|---|---|
| Deepgram | nova-3-general | 30+ languages | Low latency, high accuracy |
| Sarvam | saarika:v2.5, saaras:v3 | Indian languages | Optimized for Hindi, Tamil, etc. |
Text-to-Speech (TTS)
Converts the LLM's text response into speech.
| Provider | Models | Voices | Notes |
|---|---|---|---|
| Deepgram | aura-2-helena-en | Multiple English voices | Natural sounding, fast |
| Sarvam | bulbul:v3-beta | anushka (F), shubh (M) | Indian language voices |
Language Model (LLM)
The brain of your agent — processes the conversation and generates responses.
| Provider | Models | Notes |
|---|---|---|
| OpenAI | gpt-4.1, gpt-4o | Best overall quality |
| Groq | llama-3.3-70b | Fastest inference |
| Anthropic | claude-sonnet-4.5 | Strong reasoning |
| OpenRouter | Various | Access to many models |
API Keys
Provider API keys can be configured at two levels:
- Global — Set in Settings → Provider Keys (applies to all agents)
- Per-agent — Override in the agent's Voice tab (takes priority)
Background Sounds
Add ambient audio during calls for a more natural experience:
| Sound | Description |
|---|---|
| None | Silent background (default) |
| Office | Office ambiance |
| Cafe | Coffee shop atmosphere |
| Rain | Rain sounds |
| White Noise | Consistent background noise |
| Nature | Birds, wind, outdoor sounds |
| Keyboard | Typing sounds |
Adjust the volume slider (0–100%) to control how loud the background sound is relative to the agent's voice.