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

# Telnyx Ultra Voices

> Use Telnyx Ultra for emotionally expressive, multilingual text-to-speech with sub-100ms time to first byte.

export const AudioPlayer = ({src, title}) => {
  return <div style={{
    marginBottom: "16px"
  }}>
      {title && <p style={{
    margin: "0 0 8px 0",
    fontSize: "14px",
    fontWeight: 500
  }}>
          {title}
        </p>}
      <audio controls preload="metadata" style={{
    width: "100%",
    display: "block"
  }}>
        <source src={src} type="audio/mpeg" />
        Your browser does not support the audio element.
      </audio>
    </div>;
};

**Telnyx Ultra** is a premium text-to-speech model that delivers natural, emotionally expressive speech across 36 languages. With sub-100ms time to first byte and support for SSML emotion tags, Ultra is built for real-time AI assistants and customer-facing voice experiences where quality and responsiveness matter.

## What makes Ultra different

| Feature                | Natural / NaturalHD | Ultra                                                     |
| ---------------------- | ------------------- | --------------------------------------------------------- |
| **Time to first byte** | \~200–300ms         | **\< 100ms**                                              |
| **Expressive mode**    | —                   | Automatic emotional interpretation with SSML emotion tags |
| **Nonverbal cues**     | —                   | `[laughter]` and other natural vocalizations              |
| **Languages**          | Varies by voice     | 36 languages                                              |

## Voice format

Ultra voices use the format:

```
Telnyx.Ultra.<voice_id>
```

Browse available Ultra voices on the [Available Voices](/docs/tts-stt/tts-available-voices) page and filter by the Ultra model.

## Expressive mode for AI Assistants

When using Ultra voices with [AI Assistants](/docs/inference/ai-assistants/no-code-voice-assistant), you can enable **expressive mode** — a toggle that lets the AI model dynamically control the emotional delivery of speech during a live conversation.

### How it works

With expressive mode enabled, the assistant's system prompt is automatically augmented with instructions for using SSML emotion tags. The AI model then decides — in real time — when and how to apply emotional expression based on the conversation context.

For example, the assistant might:

* Use an excited tone when delivering good news.
* Respond with empathy when a customer describes a problem.
* Insert `[laughter]` for natural, friendly moments.
* Speak neutrally for matter-of-fact information.

This "director-style" approach means you don't need to hard-code emotions into your prompt — the AI interprets the emotional subtext naturally, with optional explicit guidance for important moments.

### Demo

Here's an example conversation with an Ultra voice assistant using expressive mode. Notice how the assistant automatically selects the appropriate emotion — `[angry]`, `[sad]`, `[happy]` — and uses `[laughter]` naturally, all without any explicit instructions in the prompt:

<AudioPlayer src="/audio/ultra-expressive-demo.mp3" title="🔊 Listen to expressive mode in action:" />

<Frame>
  <img src="https://mintcdn.com/telnyx/6HnegDj7NgZUFT6I/img/ultra-expressive-mode-demo.png?fit=max&auto=format&n=6HnegDj7NgZUFT6I&q=85&s=48d326946aff58b2396b0eb1965e0f32" alt="Conversation transcript showing an AI assistant using expressive mode — responding with angry, sad, and happy emotions plus laughter based on the user's requests" width="1108" height="1290" data-path="img/ultra-expressive-mode-demo.png" />
</Frame>

### Enable in the portal

1. Go to your assistant in the [Telnyx Portal](https://portal.telnyx.com/#/app/ai/assistants).
2. Under **Voice Settings**, select a **Telnyx Ultra** voice.
3. Toggle **Expressive Mode** on.
4. Save your assistant.

<Frame>
  <img src="https://mintcdn.com/telnyx/93EkNzE8M3fjEz_c/img/ultra-voice-settings-expressive-mode.png?fit=max&auto=format&n=93EkNzE8M3fjEz_c&q=85&s=e8a4d9333d29ddc394c47e28f1a07c3f" alt="AI Assistant voice settings in the Telnyx Portal showing a Telnyx Ultra voice selected and the Expressive Mode toggle enabled" width="1512" height="857" data-path="img/ultra-voice-settings-expressive-mode.png" />
</Frame>

### Enable via API

Set `expressive_mode: true` in your assistant's `voice_settings`:

```bash theme={null}
curl -X PATCH "https://api.telnyx.com/v2/ai/assistants/YOUR_ASSISTANT_ID" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "voice_settings": {
      "voice": "Telnyx.Ultra.YOUR_VOICE_ID",
      "expressive_mode": true
    }
  }'
```

<Warning>
  `expressive_mode` is only supported for Telnyx Ultra voices (voices starting with `Telnyx.Ultra.`). Enabling it with a non-Ultra voice will return a validation error.
</Warning>

## SSML emotion reference

When expressive mode is enabled, the assistant can use these SSML emotion tags in its responses. You can also use these tags with Ultra voices in [Call Control speak commands](/docs/voice/programmable-voice/tts).

### Format

Place an `<emotion>` tag before the text you want to affect:

```
<emotion value="EMOTION" />Your text here.
```

### Available emotions

**Primary emotions (best quality):**

| Tag                           | Use for                           |
| ----------------------------- | --------------------------------- |
| `<emotion value="angry" />`   | Firm, assertive delivery          |
| `<emotion value="excited" />` | Energetic, enthusiastic responses |
| `<emotion value="content" />` | Calm, satisfied tone              |
| `<emotion value="sad" />`     | Empathetic, subdued delivery      |
| `<emotion value="scared" />`  | Anxious, worried tone             |

**Additional emotions:**

`happy`, `enthusiastic`, `curious`, `calm`, `grateful`, `affectionate`, `sarcastic`, `surprised`, `confident`, `hesitant`, `apologetic`, `determined`, `frustrated`, `disappointed`, and more.

### Nonverbalisms

Insert `[laughter]` directly in the text for natural laughing:

```
That's a great joke! [laughter] Okay, let me help you with that.
```

### Pauses

Use SSML `<break>` tags to add explicit pauses to Ultra speech. Set the pause length with the `time` attribute:

```
Hello, thank you for calling. <break time="0.2s"/> This is Alex. How can I help you today?
```

For natural conversational pacing, start with short pauses like `0.2s` or `0.3s`, then adjust based on how the voice sounds in your use case.

<Tip>
  You don't need emotion tags or break tags for every sentence. Ultra naturally interprets emotional subtext and pacing from the text itself — use explicit tags sparingly for ambiguous readings, important moments, or places where you need a consistent pause. Omitting the tag is equivalent to neutral delivery and produces the most natural speech.
</Tip>

## Language support

Ultra supports 36 languages via the `language_boost` setting, which improves pronunciation accuracy for the target language:

Arabic, Bengali, Bulgarian, Chinese, Czech, Danish, Dutch, English, Finnish, French, German, Gujarati, Hebrew, Hindi, Indonesian, Italian, Japanese, Korean, Malay, Marathi, Māori, Norwegian, Polish, Portuguese, Punjabi, Romanian, Russian, Slovak, Spanish, Swedish, Tamil, Telugu, Thai, Turkish, Ukrainian, and Vietnamese.

Set `language_boost` in your assistant's voice settings to improve pronunciation for the target language.

## Next steps

<CardGroup cols={2}>
  <Card title="Available Voices" icon="microphone" href="/docs/tts-stt/tts-available-voices">
    Browse Ultra voices and filter by language and gender.
  </Card>

  <Card title="Voice Design Lab" icon="palette" href="/docs/voice/voice-design-lab">
    Design custom voices from natural language prompts.
  </Card>

  <Card title="AI Assistants" icon="robot" href="/docs/inference/ai-assistants/no-code-voice-assistant">
    Build voice AI assistants using Ultra with expressive mode.
  </Card>

  <Card title="Call Control TTS" icon="phone" href="/docs/voice/programmable-voice/tts">
    Use Ultra voices with Call Control speak commands.
  </Card>

  <Card title="TTS WebSocket Streaming" icon="waveform-lines" href="/docs/tts-stt/tts-websocket-streaming">
    Stream text to the TTS API and receive audio in real time.
  </Card>
</CardGroup>