Provider Nodes
Configure LLM, Text-to-Speech, and Speech-to-Text providers for your flow.
Provider nodes supply AI services to your flow. Every flow requires one LLM provider, one TTS provider, and one STT provider.
LLM Providers
The LLM powers conversational intelligence — understanding caller intent, generating responses, and evaluating transitions.
OpenAI
Google Gemini
Anthropic
Grok (xAI)
Azure OpenAI
For organizations using Azure-hosted OpenAI models. Requires your Azure endpoint URL.
| Setting | Description |
|---|---|
| Endpoint | Your Azure OpenAI endpoint URL (required) |
| Model | Deployed model name |
| Temperature | 0.0-2.0 |
LLM configuration
| Setting | Description |
|---|---|
| Model | Select the specific model |
| Temperature | Response randomness. Range: 0–2. Lower = more deterministic. |
| Max tokens | Maximum tokens per response |
| Priority tier | 2x pricing for faster inference and higher availability |
TTS Providers
The TTS provider converts agent text responses into spoken audio.
ElevenLabs
ElevenLabs settings
| Setting | Range | Description |
|---|---|---|
| Voice | — | Select from premade, cloned, generated, or professional voices |
| Stability | 0.0–1.0 | Voice consistency. Higher = more stable, lower = more expressive. |
| Similarity | 0.0–1.0 | How closely output matches the original voice sample |
| Style | 0.0–1.0 | Style variation. |
| Speaker boost | on/off | Enhances clarity and presence. |
| Speed | 0.7–1.2 | Playback speed. |
Cartesia
Cartesia settings
| Setting | Range | Description |
|---|---|---|
| Voice | — | Select from voice library. Supports masculine, feminine, and gender-neutral. |
| Emotion | 54 options | sonic-3 only. See emotion list below. |
| Speed | 0.6–1.5 | Playback speed. Default: 1.0. |
| Volume | 0.5–2.0 | Output volume. Default: 1.0. |
Supported emotions (sonic-3)
Positive — Neutral, Happy, Excited, Enthusiastic, Elated, Euphoric, Triumphant, Amazed, Surprised, Flirtatious, Curious, Content, Peaceful, Serene, Calm, Grateful, Affectionate, Trust, Sympathetic, Anticipation, Mysterious, Proud, Confident
Negative — Angry, Mad, Outraged, Frustrated, Agitated, Threatened, Disgusted, Contempt, Envious, Sarcastic, Ironic, Sad, Dejected, Melancholic, Disappointed, Hurt, Guilty, Bored, Tired, Rejected, Nostalgic, Wistful, Apologetic, Hesitant, Insecure, Confused, Resigned, Anxious, Panicked, Alarmed, Scared
Other — Distant, Skeptical, Contemplative, Determined
STT Providers
The STT provider transcribes caller speech into text for the LLM.
Deepgram
Deepgram settings
| Setting | Description |
|---|---|
| Language | Transcription language |
| Keywords | Boost recognition of specific words or phrases |
Cartesia
Cartesia STT settings
| Setting | Description |
|---|---|
| Language | Transcription language |
| Model | STT model to use |
Soniox
Soniox settings
| Setting | Description |
|---|---|
| Language | Transcription language |
| Model | STT model to use |
AssemblyAI
AssemblyAI settings
| Setting | Description |
|---|---|
| Language | Transcription language |
ElevenLabs STT
ElevenLabs STT settings
| Setting | Description |
|---|---|
| Language | Transcription language |
| Model | Scribe v2 model |
Telephony
Transport layer for connecting calls.