> ## Documentation Index
> Fetch the complete documentation index at: https://docs.sentivue.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Model Configurations

> Workflows need AI Models to work, like LLM (Large Language Model), TTS (Voice) and STT (Transcriber). You can use any of your faviourite providers with SentiVue Talk Platform to run your Workflow.

## How Model Configuration Works

SentiVue Talk uses a **two-level configuration system** for AI models:

1. **Global configuration** — A single set of model settings (LLM, TTS, STT) that applies to **all workflows** by default.
2. **Workflow-level overrides** — Optional per-agent settings that override the global configuration for specific services.

If no overrides are set for a workflow, it uses the global configuration as-is.

<Note>
  Workflow-level overrides are **selective** — you can override only the services you want to change. For example, you can override just the LLM provider for a specific workflow while keeping the global TTS and STT settings. There is no need to reconfigure every service.
</Note>

## Global Configuration

The global configuration is the default model setup shared across all your workflows. SentiVue Talk ships with its own models by default, so you get model credits to start with as soon as you sign up.

To configure the global models, go to [**Model Configurations**](https://app.sentivue.com/talk/model-configurations) in your dashboard.

From here you can configure each service:

| Service               | What it does                                                                                  |
| --------------------- | --------------------------------------------------------------------------------------------- |
| **LLM**               | The language model that generates responses (e.g., OpenAI GPT-4.1, Anthropic Claude)          |
| **TTS (Voice)**       | The text-to-speech model that converts responses to spoken audio (e.g., ElevenLabs, Cartesia) |
| **STT (Transcriber)** | The speech-to-text model that transcribes user speech (e.g., Deepgram, AssemblyAI)            |
| **Realtime**          | A single speech-to-speech model that handles LLM, TTS, and STT in one (e.g., Gemini Live)     |
| **Avatar**            | Optional. An animated video avatar shown on web calls (HeyGen LiveAvatar)                     |

Select a provider, then choose the model, voice, or language you want. Credentials are not set here — add the provider once under [Connections](/talk/configurations/connections) and it becomes available to select.

## Per-workflow overrides

You can override the global model configuration for any individual workflow. This is useful when different workflows have different requirements — for example, a customer support workflow might use a faster, cheaper LLM while a sales workflow uses a more capable one.

### Configuring overrides

1. Open the workflow you want to customize.
2. Go to **Settings** in the workflow detail page.
3. Select the **Model Overrides** tab.
4. You will see tabs for each service: **LLM**, **Voice** (TTS), **Transcriber** (STT), and **Avatar**.
5. Toggle **Override** on for the service you want to change.
6. Configure the provider, model, and other settings as needed.
7. Save your changes.

### Selective overrides

Each service can be toggled independently. When an override is **off** for a service, the workflow inherits the global setting for that service. When an override is **on**, the workflow uses the override setting instead.

| LLM Override | TTS Override | STT Override | Result                         |
| ------------ | ------------ | ------------ | ------------------------------ |
| Off          | Off          | Off          | Global config for all services |
| On           | Off          | Off          | Custom LLM, global TTS and STT |
| Off          | On           | Off          | Global LLM and STT, custom TTS |
| On           | On           | On           | Custom config for all services |

For example, if you only want to change the voice for one workflow:

1. Leave the LLM and Transcriber overrides **off**.
2. Toggle the Voice override **on**.
3. Select a different TTS provider or voice.
4. That workflow uses your custom voice while keeping the global LLM and STT.

### Realtime mode override

You can also switch an individual workflow to use a **Realtime** provider (such as Gemini Live) even if the global configuration uses standard LLM + TTS + STT. Toggle the **Realtime** switch in the Model Overrides tab, then configure the realtime provider, model, and voice.

<Note>
  When a workflow uses a Realtime provider, it replaces the separate TTS and STT services with a single speech-to-speech model. An **LLM** is still required alongside the Realtime model — it's used for out-of-band tasks like variable extraction and QA analysis, which the realtime service does not handle. Context compaction is not applicable in Realtime mode and is ignored if enabled.
</Note>

## Avatars

An avatar adds an animated video presenter to a web call. Pick one in the **Avatar** step, then switch it on wherever the call starts — see [Avatar](/talk/configurations/avatar).