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

# Create and configure an AI assistant

> Walk through creating a Talkturo AI assistant from a template, then configure the language model, temperature, and speech transcription settings.

Creating an assistant takes about two minutes. You pick a template that matches your use case, give the assistant a name, then fine-tune the model and transcriptor settings for the best call quality. This page covers the full creation flow and both configuration tabs in detail.

## Create an assistant

<Steps>
  <Step title="Open the Assistants page">
    In the left sidebar, click **Assistants**. You'll see a list of all existing assistants for your account.
  </Step>

  <Step title="Click Create New Assistant">
    Click the **Create New Assistant** button in the top-right corner. The creation dialog opens.
  </Step>

  <Step title="Choose a template">
    Select the template that best matches your use case. Each template comes pre-loaded with a starting system prompt, a default voice, and an inbound or outbound direction.

    | Template                 | Direction | Description                                                             |
    | ------------------------ | --------- | ----------------------------------------------------------------------- |
    | **Blank template**       | —         | Start from scratch with no pre-filled prompt                            |
    | **Support agent**        | Inbound   | A dedicated support agent ready to resolve customer issues              |
    | **Sales agent**          | Inbound   | A professional agent who helps incoming callers find the right solution |
    | **Appointment setter**   | Outbound  | Specialized in scheduling and managing appointments efficiently         |
    | **Sales caller**         | Outbound  | A proactive outbound agent focused on lead generation and conversion    |
    | **Language teacher**     | Inbound   | Helps callers practice conversational language skills                   |
    | **Mindfulness guide**    | Inbound   | Guides callers through meditation and mindfulness practices             |
    | **Healthcare assistant** | Inbound   | Provides general health information and guidance                        |
    | **Shopping advisor**     | Outbound  | Helps callers find the right products                                   |

    You can search templates by name, description, or category using the search box in the dialog.
  </Step>

  <Step title="Name your assistant">
    Type a name in the **Assistant name** field. The name pre-fills based on the template you selected, but you can change it to anything that helps you identify the assistant later (for example, "EU Support Bot" or "Q2 Outreach Caller").
  </Step>

  <Step title="Click Create Assistant">
    Click **Create Assistant**. The assistant is created and you land on its detail page, where you can configure each tab.
  </Step>
</Steps>

## Configure the Model tab

The Model tab controls which language model the assistant uses to generate responses and how it behaves.

<Steps>
  <Step title="Select a provider">
    Choose a provider from the **Provider** dropdown. Talkturo supports:

    | Provider          | Notes                                         |
    | ----------------- | --------------------------------------------- |
    | **OpenAI**        | GPT-4o, GPT-4o mini, GPT-4.1, GPT-5, and more |
    | **Google Gemini** | Gemini 2.5 Pro, 2.5 Flash, 2.0 Flash          |
    | **Anthropic**     | Claude 3.5 Sonnet, Claude 3.5 Haiku           |
    | **DeepSeek**      | DeepSeek V3                                   |
    | **Qwen**          | Qwen3 235B                                    |
    | **Kimi**          | Kimi K2 Instruct                              |
  </Step>

  <Step title="Select a model">
    After choosing a provider, the **Model** dropdown populates with the available models for that provider. The first model in the list is selected by default.

    <Tip>
      For most voice call use cases, a "mini" or "flash" variant gives the best balance of response speed and quality. Faster responses reduce the pause the caller experiences between speaking and hearing a reply.
    </Tip>
  </Step>

  <Step title="Set Temperature">
    Use the **Temperature** slider (0–2) to control how varied the assistant's responses are.

    * **Lower values (0–0.5):** More focused and consistent — good for support or compliance-heavy scenarios.
    * **Higher values (1–2):** More creative and varied — better for conversational or sales assistants.
  </Step>

  <Step title="Set Max Tokens">
    Enter a value in **Max Tokens** to limit how long each assistant response can be. The default placeholder is 250 tokens, which is a reasonable starting point for a voice call where responses should be concise.

    <Note>
      Very high max token values can cause long pauses on calls because the assistant generates more text before speaking. Keep responses short for voice interactions.
    </Note>
  </Step>

  <Step title="Save your changes">
    Click **Save Changes** at the top of the assistant page to apply your model settings.
  </Step>
</Steps>

## Configure the Transcriptor tab

The Transcriptor tab controls how the assistant converts the caller's speech to text. Choosing the right provider and language directly affects transcription accuracy.

<Steps>
  <Step title="Select a provider">
    Choose one of the supported speech-to-text providers:

    | Provider               | Models available                                                                                         |
    | ---------------------- | -------------------------------------------------------------------------------------------------------- |
    | **Deepgram** (default) | Flux General, Nova-3, Nova-3 Medical, Nova-2, Nova-2 Medical, Nova-2 Conversational AI, Nova-2 Phonecall |
    | **AssemblyAI**         | Universal Streaming, Universal Streaming Multilingual                                                    |
    | **Cartesia**           | Ink Whisper                                                                                              |
    | **ElevenLabs**         | Scribe V2 Realtime                                                                                       |
  </Step>

  <Step title="Select a model">
    After picking a provider, choose the model that fits your use case. Deepgram **Nova-3** is a strong general-purpose choice. Use **Nova-3 Medical** or **Nova-2 Medical** for healthcare conversations with medical terminology. Use **AssemblyAI Universal Streaming Multilingual** when callers may switch between languages mid-call.
  </Step>

  <Step title="Select a language">
    Choose the primary language your callers speak. Available languages depend on the model selected. For example:

    * Deepgram Nova-3 and Nova-2 support English (US, UK), Spanish, French, German, Portuguese, and a **Multilingual** mode.
    * AssemblyAI Universal Streaming Multilingual adds Italian and Portuguese.
    * Cartesia Ink Whisper adds Chinese, Japanese, Korean, and Russian.
    * ElevenLabs Scribe V2 Realtime supports English, Spanish, French, German, Portuguese, Japanese, and Chinese.
  </Step>

  <Step title="Save your changes">
    Click **Save Changes** to apply the transcription settings.
  </Step>
</Steps>