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. Not supported by every model — see below. |
| Max tokens | Maximum tokens per response |
| Priority tier | 2x pricing for faster inference and higher availability |
Temperature support
Some models reject a custom temperature and use reasoning defaults instead. When a restricted model is selected, temperature is stripped from the flow definition before it reaches the bot and the UI — setting a value has no effect.
The restriction is driven by model metadata, not a hardcoded list. Currently restricted: gpt-5, gpt-5-mini, gpt-5.1-chat-latest, gpt-5.2-chat-latest, and claude-opus-4-8.
The model's llmCapabilities.temperature field in the provider list response indicates support. The model table above renders this capability inline when showCapabilities is set.
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
Google TTS
Gemini TTS models (gemini-2.5-flash-tts for low latency, gemini-2.5-pro-tts for highest quality). 30 named voices, 23 languages.
Google TTS settings
| Setting | Description |
|---|---|
| Voice | Named Gemini voice (e.g., Kore) |
| Language | Output language |
| Style prompt | Natural-language instruction that steers delivery style |
xAI TTS
Streaming synthesis with word-level timestamps. 5 voices, 20 languages.
xAI TTS settings
| Setting | Range | Description |
|---|---|---|
| Voice | — | xAI voice. Default: eve. |
| Language | — | Output language. Default: en. |
| Speed | 0.7–1.5 | Playback speed. |
Rime
mistv2 for low-latency streaming (300+ voices, English/Spanish), arcana for premium expressiveness (English/Spanish/French/German).
Rime settings
| Setting | Description |
|---|---|
| Voice | Rime voice. Default: cove. |
| Language | Output language. Default: en. |
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 |
ElevenLabs STT
ElevenLabs STT settings
| Setting | Description |
|---|---|
| Language | Transcription language |
| Model | Scribe v2 model |
Google STT
Streaming recognition with chirp_3 (best accuracy, 100+ languages), chirp_2, or latest_long (long-form conversation model).
Google STT settings
| Setting | Description |
|---|---|
| Language hints | One or more expected languages to bias recognition |
| Location | Google Cloud recognition location. Default: global. |
xAI STT
grok-stt — real-time streaming with word-level timestamps and telephony support across 25 languages.
xAI STT settings
| Setting | Description |
|---|---|
| Language | Transcription language, or auto-detect |
| Diarization | Label speech per speaker |
Amazon Transcribe
Streaming recognition with word-level timestamps and telephony (8 kHz) support across 30+ languages.
Amazon Transcribe settings
| Setting | Description |
|---|---|
| Language | Transcription language |
| Region | AWS region for the streaming endpoint |
Telephony
Transport layer for connecting calls.