# Models
URL: /tts/models

Learn about latest Text-to-Speech models, changelog, and deprecations.

Soniox Text-to-Speech is built for the hardest parts of speech generation. It delivers native-speaker-quality speech in 60+ languages, with hallucination-free output and accurate pronunciation of alphanumerics such as phone numbers, email addresses, and IDs.

This page lists the currently available models, along with release notes and important updates.

***

## Current models

{/*TABLE START */}

{/* NOTE: Width is set so that we have maximum of 2 lines in 'Example' column. */}

{/* NOTE: Font size is set so the table doesn't look "too big".*/}

<div>
  | <div style={{ width: "150px" }}>Model </div> | {" "} <div style={{ width: "70px" }}>Type</div> | Status                                           |
  | -------------------------------------------- | ----------------------------------------------- | ------------------------------------------------ |
  | **tts-rt-v2**                                | Real-time                                       | **Active**                                       |
  | **tts-rt-v1**                                | Real-time                                       | **Deprecated**<br />Will be removed Aug 31, 2026 |
</div>

{/* TABLE END */}

***

## Aliases

Aliases provide a stable reference so you don’t need to change your code when newer versions are released.

| Alias                 | Points to   | Notes |
| --------------------- | ----------- | ----- |
| **tts-rt-v1-preview** | `tts-rt-v1` |       |

***

## Changelog

### Aug 11, 2026

#### Overview

Soniox TTS v2 is now generally available.

* `tts-rt-v2` is available to all API customers and deployed in all Soniox regions: US, EU, JP, and IN.

#### Key improvements

* Natural, expressive speech across more than 60 languages
* Direct control over emotion, delivery, and vocal reactions through audio tags
* High-fidelity voice cloning
* Natural language switching within the same sentence
* Even more precise pronunciation of names, terminology, numbers, codes, addresses, and identifiers
* Reduced silence between sentences and punctuation for more responsive conversations

#### API compatibility

The `tts-rt-v2` model is fully compatible with the existing `tts-rt-v1` model and Soniox Text-to-Speech API.
To upgrade, simply replace the model name in your API request: `{ "model": "tts-rt-v2" }`

#### Deprecation notice

The `tts-rt-v1` model will be removed on August 31, 2026.
After August 31, 2026, requests using `tts-rt-v1` will automatically route to `tts-rt-v2` with no service interruption and no API changes required.

### April 29, 2026

#### Overview

Soniox TTS is now generally available.

* The preview model `tts-rt-v1-preview` is now available as the production model `tts-rt-v1`.
* `tts-rt-v1` is available to all API customers and deployed in all Soniox regions: US, EU, and JP.
* For backward compatibility, `tts-rt-v1-preview` now points to `tts-rt-v1` with no service interruption. We recommend updating your API requests to use `tts-rt-v1`.

### April 23, 2026

#### Overview

`tts-rt-v1-preview` is the first Soniox Text-to-Speech model, released in preview to gather developer feedback and guide further improvements before general availability.

#### Key capabilities

* Native-speaker-quality speech in 60+ languages
* Hallucination-free generation, with no invented words, dropped content, or unexpected substitutions
* Accurate rendering of alphanumerics such as email addresses, phone numbers, street addresses, IDs, and codes
* Streaming generation before the sentence ends for ultra-low-latency voice systems
* Multiple voices that work across all supported languages
* Configurable audio formats, sample rates, and bitrates
* Support for both WebSocket and REST APIs