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

# TTS streaming

> Learn about TTS streaming in Voice for real-time text-to-speech audio delivery, enabling natural voice agent conversations with minimal latency.

The *TTS streaming* feature delivers synthesized speech to your voice agent as it's generated, rather than waiting for the entire response to finish processing. It enables faster, more natural-sounding conversations.

Standard TTS systems wait for the entire text to be processed before playing any audio, which introduces a noticeable delay, especially with longer texts. TTS streaming instead processes text in segments and plays each one back as soon as it's synthesized.

<video width="650" height="400" controls autoPlay title="Streaming vs. standard TTS" aria-label="A video comparing standard text-to-speech processing, which waits for the full text before generating audio, with streaming text-to-speech, which begins playback as segments are synthesized.">
  <source src="https://docscognigyassets.blob.core.windows.net/assets/traditional-tts-vs-tts-streaming.mp4" />
</video>

> [!NOTE]
>
> Some speech providers use `streaming` to describe their API's connection method, for example, a websocket-based API for submitting multiple texts. This concept is different from TTS streaming in Voice, which refers to audio playout: how quickly synthesized audio starts playing back to the caller.

## Key benefits

* **Lower response latency.** Audio playback starts as soon as the first words are synthesized, instead of after the full text is processed.
* **More natural conversation flow.** Reduced time-to-first-audio makes voice agent responses feel closer to real-time human conversation, especially with longer text.

## Prerequisites

* A [voice flow agent](https://docs.cognigy.com/ai/agents/develop/flow-agents/voice.md) configured.
* A configured [speech service](https://docs.cognigy.com/voice-gateway/webapp/speech-services).

## Restrictions

* The following speech providers don't support TTS streaming: AWS, Google, Nuance, Speechmatics, and Deepgram Flux.
* For ElevenLabs, Voice uses the [ElevenLabs streaming API](https://elevenlabs.io/docs/api-reference/text-to-speech/stream). The following parameters aren't supported and can't be specified in **Extra Options**:
  * `seed`
  * `previous_request_ids`
  * `next_request_ids`
  * `apply_text_normalization`
  * `apply_language_text_normalization`
  * `use_pvc_as_ivc`
  * `pronunciation_dictionary_locators`

## Configure TTS streaming

To activate streaming for your voice agent, follow these steps:

> [accordion] 1. Configure the speech service
>
> 1. In the navigation menu, select **Speech**.
> 2. On the **Speech services** page, select an existing speech service or [create a new one](https://docs.cognigy.com/voice-gateway/webapp/speech-services) by clicking **Add a speech service** in the upper-right corner.
> 3. On the **Add Speech service** page, make sure that the **Use for text-to-speech** option is activated.
> 4. Activate the **Enable text-to-speech streaming** option.
> 5. *(Optional)* For ElevenLabs, configure the **Extra Options** field to customize the TTS streaming behavior. See the list of unsupported parameters in the [Restrictions](#restrictions) section.
> 6. Click **Save**.

> [accordion] 2. Configure the set session config node in Cognigy
>
> 1. Go to the Set Session Config node in your flow.
> 2. In the **Synthesizer (TTS)** section, select your speech service from the **TTS Vendor** list.
> 3. Configure **TTS Language** and **TTS Voice** as needed.

## More information

* [Speech services](https://docs.cognigy.com/voice-gateway/webapp/speech-services)
* [TTS and STT vendors](https://docs.cognigy.com/voice-gateway/references/tts-and-stt-vendors.md)