> ## 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.

# Models & voices

> Choose models, preview voices, clone your own, and turn on reliable fallbacks

An assistant's models decide how well it understands the caller and how it sounds. The assistant editor is where you pick them, tune the speaking style, clone a voice of your own, and switch on fallbacks that keep a call going if a model fails mid-call.

## Model catalog

The assistant editor shows a curated catalog of models available to your workspace:

| Type               | Purpose                                                    |
| ------------------ | ---------------------------------------------------------- |
| Language model     | Understands the conversation and decides what to say or do |
| Speech recognition | Converts the caller's speech into text                     |
| Text-to-speech     | Produces the assistant's spoken voice                      |
| Realtime           | Listens and speaks in one low-latency model                |

Availability depends on your workspace and selected [engine mode](/assistants/engine-modes). Models marked **Recommended** are good starting points; **Low latency** highlights options suited to responsive phone conversations.

When **Fallbacks & Guardrails** is included, you can choose models separately for pipeline, realtime, and half-cascade assistants. Otherwise, the assistant uses the recommended automatic selection.

## Temperature

In Pipeline mode, **Temperature** controls how closely the language model sticks to your prompt versus varying its wording. The slider runs from 0 — deterministic and on-script — upward to more creative, improvised replies. **0.5–0.8** is a typical range for phone conversations.

Treat it as final fine-tuning, not a substitute for a well-written prompt:

1. Finish the prompt first — role, goals, boundaries, tone.
2. Start low.
3. Raise it in small steps, only once the baseline sounds good.
4. Test and compare after each change.

Raise it when replies sound stiff or formulaic and the use case tolerates some improvisation. Keep it low when consistency, compliance, or precise wording matter more than natural variation.

## Voice library

Use the voice picker to filter by language and voice characteristics, then play a sample before saving.

* **Assistant voice** — the default voice for the assistant.
* **Voice per flow agent** — give individual [flow](/flow-builder/nodes) agents distinct voices.
* **Voice per language** — change the voice together with [automatic language switching](/assistants/languages).
* **Cloned voices** — when included in your plan, add a private custom voice and use it like a library voice.

When recording a sample to clone, use clear, high-quality audio with steady, natural delivery and no background noise — and only clone a voice you have permission to use (see [Voice cloning consent](/assistants/voice-cloning-consent)).

Cloning is also available as `POST /api/v1/voices/clone` (multipart upload, `voices:write` scope) and the MCP tool `clone_voice`. Both the dashboard picker and the API call into the same cloning path, gated by the same **Clone your own voice** add-on and plan capacity — the API can't create a cloned voice the dashboard wouldn't also allow.

## Speaking style

The available controls adapt to the selected model. Depending on the voice, you may see:

* speaking rate and output volume;
* stability, similarity, or expressiveness;
* free-text style instructions;
* a pronunciation dictionary for names, abbreviations, and specialist terms;
* filters that prevent markdown and emoji from being read aloud.

Only compatible controls are shown and applied.

<Tip>
  Pick the voice first, then tune one control at a time — stability, similarity, or rate — and listen to a realistic phrase from your actual call flow before changing the next one.
</Tip>

When the **Dynamic emotions** setting (Expressive Mode) is available for the selected voice, the assistant can adapt emotion, pacing, emphasis, pauses, and supported non-verbal sounds to the conversation. It applies to pipeline and half-cascade assistants; realtime speech models handle vocal expression natively. Availability depends on the selected voice, and unsupported delivery cues are not applied. Transcripts remain clean and do not include delivery markup.

## Speech recognition glossary

Open **Assistant settings → Voice → Speech recognition** to add customer, product, and proper names that should be transcribed accurately. The glossary affects the transcript; use the pronunciation dictionary separately when a term also needs a special spoken form.

If **Automatic term detection (Beta)** is available and enabled, the assistant can recognise additional terms for the current call. This may add AI usage. Detected terms are not added to your saved glossary.

## Fallback chains

**Fallback chains** is a single switch, not a set of choices you configure. Turn it on, and if the primary speech-recognition, language-model, or voice service times out, errors, or drops mid-call, the assistant automatically moves to a compatible backup so the conversation keeps going instead of dropping. Famulor selects and maintains which backup each chain falls through to — there's no picker for the backup models themselves.

<Note>
  Fallback chains ship with the **Fallbacks & Guardrails** add-on; check **Settings → Plan** for availability. Failing over doesn't add a separate charge on its own — a call that fails over still bills at the normal call-minute rate.
</Note>

<Note>
  Test important assistants after changing models, voices, or languages. A short simulation is usually enough to catch pronunciation and timing differences.
</Note>