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

# Assistant Best Practices

> Quick guide to fine-tune mode, transcriber, model, and other settings for the best call experience

<Info>
  Last updated: Feb. 1, 2026
</Info>

Getting great results often comes down to picking the right engine settings. Use this checklist when configuring a Famulor assistant.

## 1. Pick a Mode

| Mode                          | Why choose it?                                   | Notes                                                                                                                                   |
| ----------------------------- | ------------------------------------------------ | --------------------------------------------------------------------------------------------------------------------------------------- |
| Speech-to-Speech (Multimodal) | Fastest turn-taking and most natural flow        | Recommended starting point. Try the Gemini 2.5 engine (beta) for the lowest latency, but note it’s experimental and may be less stable. |
| Pipeline                      | Maximum control over voice and long-form replies | If you select Pipeline, continue to the Transcriber step below.                                                                         |

Want to know more about the differences? See the [Assistant Modes guide](/en/ai-assistants/assistant-modes).

<Tip>
  Record the same scenario in both modes and compare response time and caller satisfaction.
</Tip>

## 2. Choose a Transcriber (Pipeline only)

| Transcriber | Accuracy | Latency         | Best for                                                                       |
| ----------- | -------- | --------------- | ------------------------------------------------------------------------------ |
| Azure       | ⭐️⭐️⭐️⭐️ | ⏱️⏱️⏱️ (slower) | Highest transcription fidelity                                                 |
| Gladia      | ⭐️⭐️⭐️   | ⏱️ (faster)     | Good all-rounder for most languages                                            |
| Deepgram    | ⭐️⭐️⭐️   | ⏱️ (faster)     | Solid alternative—test which performs better for your language and audio setup |

<Tip>
  Different languages, accents, and background noise can affect each engine differently. Run a quick A/B test and keep the best performer.
</Tip>

## 3. Select an LLM Model

| Model                 | Strengths                                   | Trade-offs                                                   |
| --------------------- | ------------------------------------------- | ------------------------------------------------------------ |
| GPT-4o                | Smartest reasoning, handles complex prompts | Slightly higher latency and cost                             |
| Gemini 2.5-Flash-Lite | Blazing-fast, still highly capable          | May miss nuance in very complex tasks—test for your use case |

<Tip>
  If speed is critical, start with Gemini 2.5-Flash-Lite. For sophisticated reasoning, use GPT-4o and offset latency by shortening replies.
</Tip>

## 4. Noise Cancellation

If callers are on speaker phone or in a quiet environment, keep noise cancellation ON. If your call volume is low or some words are “clipped,” turn it OFF so the transcriber gets the full waveform.

<Tip>
  If the assistant isn’t hearing you well, try turning noise cancellation off.
</Tip>

## 5. Conversation Timers

| Parameter            | Recommended | Why                                                                |
| -------------------- | ----------- | ------------------------------------------------------------------ |
| Re-engagement        | ≈ 30 s      | Gives callers enough time to think. Lower values can feel pushy.   |
| Max silence duration | ≈ 60 s      | Prevents premature hang-ups while still ending truly silent calls. |

<Info>
  Test different values in real calls—too low can interrupt, too high leaves awkward gaps.
</Info>

## 6. Initial Message

| Mode             | How it’s used                              | Best practice                                                                                                |
| ---------------- | ------------------------------------------ | ------------------------------------------------------------------------------------------------------------ |
| Pipeline         | Read exactly as written (converted by TTS) | Write the greeting verbatim: “Hello, this is Alex from …”.                                                   |
| Speech-to-Speech | Interpreted as a prompt by the model       | Include instructions like “Greet the customer and say …” or prepend `say exactly:` to ensure literal output. |

## 7. Ambient sound

Ambient sound adds subtle background noise to the assistant’s voice and is enabled by default.

<Tip>
  If the assistant isn’t hearing you well, turn off ambient sound or lower the ambient volume.
</Tip>

## 8. Endpointing sliders

Control when your assistant starts talking with the endpointing sensitivity slider at the bottom of assistant settings.

| Setting            | Effect                                                | Use when                                   |
| ------------------ | ----------------------------------------------------- | ------------------------------------------ |
| Lower sensitivity  | Assistant responds faster after caller stops speaking | You want snappy, quick-turn conversations  |
| Higher sensitivity | Assistant waits longer before responding              | Callers give longer, more detailed replies |

<Tip>
  If your assistant cuts off callers mid-sentence, increase sensitivity. If responses feel sluggish, decrease it.
</Tip>

## 9. Debug using the call transcript

<Steps>
  <Step title="Open Call history">
    Go to the Call history page in your dashboard.
  </Step>

  <Step title="Select your latest test call">
    Open the most recent call you placed for this assistant.
  </Step>

  <Step title="Inspect transcript and function calls">
    Review the transcript, function calls, and parameters to identify timing or logic issues.

    <Check>
      Confirm the assistant is using the expected mode, model, and tools per your configuration.
    </Check>
  </Step>
</Steps>

## 10. Still have questions?

If you need help, contact our support team via the chat widget inside the app.

## 11. Debug with the Test Assistant (chat)

<Steps>
  <Step title="Open your assistant">
    Open the assistant you want to debug in the Famulor app.
  </Step>

  <Step title="Switch to the Test Assistant tab">
    At the top of the page, click the <strong>Test Assistant</strong> tab.
  </Step>

  <Step title="Start a free chat session">
    Chat with your assistant to validate prompts, tools, and behavior. These chats are free and do not consume call minutes.
  </Step>

  <Step title="Ensure you have chat credits">
    Make sure you have at least one chat credit available. If you do not have any, go to <a href="https://app.famulor.de/credits">the credits page</a> and convert your minute credits into chat credits.
  </Step>
</Steps>

***

<CardGroup cols={2}>
  <Card title="Assistant Modes" icon="bolt" href="/en/ai-assistants/assistant-modes">
    Understand the differences between Pipeline and Speech-to-Speech.
  </Card>

  <Card title="Voice Selection & Cloning" icon="microphone" href="/en/ai-assistants/voice-selection">
    Choose a built-in voice or your custom-cloned brand voice.
  </Card>
</CardGroup>