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

# DialNexa Supported Voices And Models Reference

> Compare supported DialNexa voice providers, voice models, language filters, selection behavior, and tuning controls.

DialNexa supported voices and voice models define how agents sound. A voice provides the speaker identity. A voice model controls how the provider synthesizes the agent response into audio.

<img src="https://mintcdn.com/dialnexa/O6bVvssz6DpTKOa0/images/documentation/screenshots/voice-selector-modal.jpg?fit=max&auto=format&n=O6bVvssz6DpTKOa0&q=85&s=8b4a6704f5030d85e47701793346c288" alt="DialNexa voice selector showing Cartesia voices, language filters, Hinglish selection, Nexa voice ID, and row language controls." style={{ width: '100%', maxWidth: '1100px', margin: '8px 0 24px', border: '1px solid #e5e7eb', borderRadius: '6px' }} width="1710" height="985" data-path="images/documentation/screenshots/voice-selector-modal.jpg" />

<img src="https://mintcdn.com/dialnexa/O6bVvssz6DpTKOa0/images/documentation/screenshots/voice-settings-popover.jpg?fit=max&auto=format&n=O6bVvssz6DpTKOa0&q=85&s=a8c1405107985195f710cdde1c028ba2" alt="DialNexa voice settings popover showing voice model, speed, stability, and volume controls." style={{ width: '100%', maxWidth: '1100px', margin: '8px 0 24px', border: '1px solid #e5e7eb', borderRadius: '6px' }} width="1710" height="985" data-path="images/documentation/screenshots/voice-settings-popover.jpg" />

<Tip>
  Choose voices by listening. Field names are useful, but they have never answered a phone call.
</Tip>

## DialNexa Supported Voices And Models

| Provider   | What users see                                                                                                                                       | Best fit                                                                                                         |
| ---------- | ---------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------- |
| ElevenLabs | Voice rows, sample playback, Nexa voice id, supported languages, and Flash v2.5 model selection where available. Default model: `eleven_flash_v2_5`. | Brand personality, broad voice auditioning, and pronunciation-sensitive use cases.                               |
| Cartesia   | Cartesia voice rows, language-aware voices, model options, speed, stability, and volume controls. Default model: `sonic-3.5-2026-05-04`.             | Fast streamed speech, clean call audio, and production agents that need a natural voice for a specific language. |

## Voice Fields

| Field               | Meaning                                                                                      |
| ------------------- | -------------------------------------------------------------------------------------------- |
| `provider`          | Public voice provider: ElevenLabs or Cartesia.                                               |
| `provider_voice_id` | Provider-specific voice identifier.                                                          |
| `id`                | DialNexa voice id. The UI can also show it as `voice_...` or `vel_...` depending on context. |
| `name`              | Display name shown in the voice selector.                                                    |
| `accent`            | Accent label used for filtering when available.                                              |
| `age_group`         | Approximate age group label where available.                                                 |
| `gender`            | Gender label used for filtering.                                                             |
| `languages`         | Language records linked to the voice.                                                        |
| `recording`         | Sample audio URL used by the play button.                                                    |

## Voice Model Fields

| Field                     | Meaning                                                                   |
| ------------------------- | ------------------------------------------------------------------------- |
| `provider`                | Voice model provider.                                                     |
| `provider_voice_model_id` | Provider model id, such as `eleven_flash_v2_5` for ElevenLabs Flash v2.5. |
| `name`                    | Model display name in the voice settings popover.                         |
| `description`             | Optional model explanation shown in tooltips.                             |
| `pricing_per_minute`      | Per-minute pricing metadata when available.                               |
| `is_deleted`              | Whether the model is unavailable for selection.                           |

## Dashboard Selection Behavior

| Behavior                                                                  | What it means                                                                          |
| ------------------------------------------------------------------------- | -------------------------------------------------------------------------------------- |
| Voice modal starts without a language filter.                             | Users see the full provider catalog first, then narrow it by language when needed.     |
| Voices can be filtered by provider, language, gender, accent, and search. | Large voice lists stay usable.                                                         |
| Each voice row can have its own language dropdown.                        | Users choose the language for the selected voice before applying it.                   |
| The Nexa voice ID copies as `vel_...`.                                    | Support, API-adjacent setup, and internal notes can refer to the same voice.           |
| ElevenLabs current dashboard path shows Flash v2.5 where supported.       | Test the visible model instead of expecting older models to appear for new selections. |
| Published versions can lock voice settings.                               | Edit a draft version when testing voice changes.                                       |

## Voice Selection Checklist

<Steps>
  <Step title="Filter by language first">
    A good English sample does not prove the voice works for Hindi-English or another language.
  </Step>

  <Step title="Play the sample">
    Use the sample to remove obvious bad fits quickly.
  </Step>

  <Step title="Run a real test call">
    Use your greeting, names, amounts, dates, and compliance lines through the actual route.
  </Step>

  <Step title="Tune the popover settings">
    Adjust voice model, speed, stability, and volume one at a time.
  </Step>

  <Step title="Review Call History">
    Listen to the recording and inspect Audio Cache behavior for repeated phrases.
  </Step>
</Steps>

## Related Reading

<CardGroup cols={2}>
  <Card title="Text To Speech" icon="volume-2" href="/docs/voice-ai/text-to-speech-and-voices">
    Compare ElevenLabs and Cartesia behavior.
  </Card>

  <Card title="Languages Voices Models And Transcribers" icon="sliders-horizontal" href="/docs/agents/languages-voices-models-and-transcribers">
    Choose the complete conversation stack.
  </Card>

  <Card title="Supported Languages" icon="languages" href="/docs/reference/supported-languages">
    Match voices to language requirements.
  </Card>

  <Card title="Testing Agents" icon="phone-call" href="/docs/agents/testing-agents">
    Listen before publishing.
  </Card>
</CardGroup>