> ## 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 Modes

> Understand the two voice generation modes available for your AI assistants and when to use each one

Famulor AI assistants support two voice generation modes. Each mode affects how caller speech is processed and how replies are generated.

<Info>
  Latency varies by language, model, and network conditions. Values below are typical ranges.
</Info>

### Quick comparison

| Mode                          | How it works                                              | Typical latency | Best for                                                   | Voice options                               |
| ----------------------------- | --------------------------------------------------------- | --------------- | ---------------------------------------------------------- | ------------------------------------------- |
| Pipeline                      | Speech-to-Text → LLM → Text-to-Speech                     | \~800–1500 ms   | Complex reasoning, dynamic prompts, multi-sentence replies | All library voices, including custom-cloned |
| Speech-to-Speech (Multimodal) | Direct speech-to-speech generation (no intermediate text) | \~300–600 ms    | Snappy back-and-forth, short and reactive replies          | Limited set; expanding over time            |

## 1. Pipeline

* **Label in UI**: Pipeline
* **How it works**: Speech-to-Text → LLM → Text-to-Speech
* **Latency**: \~800 – 1500 ms (depends on language & model)
* **Best for**: Complex reasoning, dynamic prompts, multi-sentence replies

Pipeline mode first transcribes the caller’s words into text, runs that text through the language model, then converts the response back to audio. It’s a flexible approach that offers maximum control:

* Supports all voices in the library (including custom-cloned voices).
* Handles long-form answers or paragraph-style responses well.
* Allows the LLM to inject variables and reference earlier context cleanly.

### When to choose Pipeline

* You need rich, multi-sentence answers (e.g., support queries, detailed explanations).
* The assistant must reason over structured data or complex prompts.
* You prefer absolute control of the spoken voice (clone or brand voice).

<Tip>
  Use Pipeline when brand voice consistency matters or when your prompts rely on structured data lookups.
</Tip>

## 2. Speech-to-Speech (Multimodal)

* **Label in UI**: Speech-to-speech
* **How it works**: Direct speech-to-speech generation (no intermediate text)
* **Latency**: \~300 – 600 ms (ultra low)
* **Best for**: Natural back-and-forth, short & reactive replies

Speech-to-speech mode skips separate transcription and TTS. Instead, it uses a multimodal model that listens and speaks directly, producing more conversational flow:

* Fast turn-taking – callers experience near-instant responses.
* Generates more expressive prosody natively (intonation, fillers).
* Currently supports a limited voice set, but more are added regularly.

### When to choose Speech-to-Speech

* The conversation needs to feel snappy (sales, booking confirmations).
* Your replies are generally short sentences or quick acknowledgements.
* You’re okay with the system-provided voice options for faster interaction.

<Warning>
  If you need a custom-cloned voice, long-form responses, or advanced prompt logic, prefer Pipeline.
</Warning>

## Switching modes

Test both modes and pick the best balance of speed and quality for your use case.

<Steps>
  <Step title="Open assistant settings">
    Go to Assistant → Settings → Voice Engine for the specific assistant.
  </Step>

  <Step title="Select a mode">
    Choose **Pipeline** or **Speech-to-speech** based on conversation style and latency needs.
  </Step>

  <Step title="Choose a voice (if using Pipeline)">
    Select a built-in voice or a custom-cloned voice. See: [Voice Selection & Voice Cloning](/en/ai-assistants/voice-selection).
  </Step>

  <Step title="Place a quick test call">
    Record two short calls—one per mode—covering your most common scenarios.

    <Check>
      Confirm acceptable latency, turn-taking, and tone consistency.
    </Check>
  </Step>

  <Step title="Decide and roll out">
    Pick the mode that best fits your flow and keep monitoring call recordings for quality.
  </Step>
</Steps>

<Tip>
  Record two calls—one in each mode—and compare perceived latency and engagement to decide what fits your flow.
</Tip>

***

<CardGroup cols={2}>
  <Card title="Voice Selection & Voice Cloning" icon="microphone" href="/en/ai-assistants/voice-selection">
    Choose a built-in voice or use your custom-cloned brand voice.
  </Card>

  <Card title="System Prompts" icon="brain" href="/en/ai-assistants/system-prompt">
    Design effective prompts to guide reasoning and responses.
  </Card>
</CardGroup>