Assistant CoreAssistant Core

AI Models

Providers, model types, and plan access currently supported by Assistant Core.

Assistant Core supports multiple AI models for chat, voice, and realtime conversations. Depending on your plan, the assistant settings will show the models available to you.

Providers

ProviderSupports
OpenAIChat, text to speech, speech to text, realtime voice
AnthropicChat
Google AIChat, realtime voice
X.AIChat, text to speech, speech to text, realtime voice
DeepSeekChat
ElevenLabsText to speech, speech to text
SonioxText to speech, speech to text
Local/Open SourceVoice activity detection

Model Types

TypeWhat it is used for
ChatAnswers questions, reasons through tasks, uses tools, and handles multimodal content when supported
Voice Activity DetectionDetects when a user starts or stops speaking
Speech to TextTranscribes spoken audio into text
Text to SpeechTurns text into spoken audio
Realtime VoiceLow-latency two-way voice conversations

Voice Models

Voice Activity Detection

ProviderModels
Local/Open SourceSilero VAD

Speech To Text

ProviderModels
OpenAIGPT-4o Transcribe, GPT-4o Mini Transcribe
ElevenLabsElevenLabs Scribe v2
SonioxSoniox STT Real-Time v4
X.AIxAI Grok STT

Text To Speech

ProviderModels
OpenAIGPT-4o Mini TTS
ElevenLabsElevenLabs Flash v2.5
X.AIGrok 2 TTS
SonioxSoniox TTS RT v1

Realtime Voice

ProviderModels
OpenAIGPT Realtime 1.5, GPT Realtime Mini
Google AIGemini 2.5 Flash Live
X.AIxAI Grok Voice Agent

Chat Models

ProviderModels
OpenAIGPT-5.4, GPT-5.4 Mini, GPT-5.4 Nano, GPT-5.1, GPT-4.1, GPT-4.1 Mini, GPT-4.1 Nano
AnthropicClaude Sonnet 4.5, Claude Haiku 4.5
Google AIGemini 2.5 Pro, Gemini 2.5 Flash, Gemma 4 31B
X.AIGrok 4.3
DeepSeekDeepSeek V4 Flash, DeepSeek V4 Pro

Plan Access

PlanAvailable models
FreeGemini 2.5 Flash, GPT-4.1 Mini
GoGemini models, including Gemini 2.5 Flash, Gemini 2.5 Pro, and Gemini 2.5 Flash Live
PlusOpenAI GPT models and Gemini models
ProAll supported models
EnterpriseAll supported models

Default Models

When you create an account or join an assistant, the following models are pre-selected. You can change them anytime in Settings.

TypeDefault Model
Chat (LLM)GPT-4.1 Mini
Text to SpeechGrok 2 TTS
Speech to TextxAI Grok STT
Voice Activity DetectionSilero VAD
Realtime VoicexAI Grok Voice Agent

Default models are the same across all plans. The difference between plans is the list of available models — higher plans unlock more models for you to switch to.

Some capabilities, including realtime voice, daily messages, devices, knowledge base documents, and voice minutes, are still limited by each plan's quota.

On this page

ProvidersModel TypesVoice ModelsVoice Activity DetectionSpeech To TextText To SpeechRealtime VoiceChat ModelsPlan AccessDefault Models