> ## 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.

# In-Call Playback

> Play Telnyx text-to-speech audio during live voice calls using the Programmable Voice API or TeXML, with options for streaming and per-call voice selection.

In-call TTS plays synthesized speech during live voice calls. Two integration paths:

## Voice API

Use the [`speak`](/api-reference/call-commands/speak-text) command to play TTS on an active call:

```bash theme={null}
curl --location 'https://api.telnyx.com/v2/calls/{call_control_id}/actions/speak' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer YOUR_API_KEY' \
--data '{
  "voice": "Telnyx.Ultra.3e1ed423-17e5-4773-b87c-25b031106e41"
}'
```

See [Voice API docs](/docs/voice/programmable-voice) for the full command reference.

## TeXML

Use the `<Say>` element:

```xml theme={null}
<Response>
  <Say voice="Telnyx.NaturalHD.astra">Your appointment is confirmed for tomorrow at 3 PM.</Say>
</Response>
```

See [TeXML docs](/docs/voice/texml) for the full `<Say>` reference.

## AI Assistants

AI Assistants use TTS for voice output. Configure the voice model in assistant settings.

See [AI Assistants](/docs/inference/ai-assistants) for voice configuration.

## Voice Selection

In-call TTS uses the same voice format as WebSocket and REST:

```
Provider.Model.VoiceId
```

All models (including Ultra) are available for in-call playback.