> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://murf.ai/api/docs/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://murf.ai/api/docs/_mcp/server.

# Changelog

## October 13, 2026

## Volume offset for Falcon 2

Falcon 2 streaming now supports **`volumeOffset`** on [Stream Speech](/api/docs/api-reference/text-to-speech/stream) and in WebSocket `voice_config`. Adjust loudness relative to the model's default output (integer **-50** to **50**, default **0**) so voice agents match phone lines, earpieces, and noisy environments without adding latency.

See [Volume offset (Falcon 2)](/api/docs/text-to-speech/speech-customization#volume-offset-falcon-2) and the [Falcon 2](/api/docs/text-to-speech-models/falcon-2) model page for suggested ranges and best practices.

## October 9, 2026

## Word Timestamps for WebSocket Streaming

You can now request per-word timing on the [WebSocket API](/api/docs/api-reference/text-to-speech/stream-input) with Falcon 2. Set `add_word_timestamps` to `true`; once enabled, it applies to the whole WebSocket connection. Falcon returns each spoken word with `start_s` and `end_s` in separate JSON frames alongside the audio.

This is especially useful for voice agents handling barge-in: you can see how much of a response had already played when the user interrupts.

Word timestamps are available in every locale except Chinese, Japanese, and Korean. See [Advanced Settings](/api/docs/text-to-speech/web-sockets/advanced-settings) for response format and timing behavior.

## October 5, 2026

## Gen2 Streaming Decommissioned

The Gen2 model has been decommissioned for the [Streaming API](/api/docs/text-to-speech/streaming). If you haven't migrated yet, use our latest [Falcon 2](/api/docs/text-to-speech-models/falcon-2) model on the [Streaming API](/api/docs/api-reference/text-to-speech/stream).

The [Gen2](/api/docs/text-to-speech-models/gen-2) model remains available for non-streaming text-to-speech through the [Synthesize Speech](/api/docs/api-reference/text-to-speech/generate) endpoint.

## July 20, 2026

## Upcoming Gen2 Streaming Deprecation

Our legacy Gen2 streaming model is set to be deprecated on 16th August 2026. We recommend migrating to our latest [Falcon 2](/api/docs/text-to-speech-models/falcon-2) model promptly.

Gen2 non-streaming text-to-speech will remain available through the [Synthesize Speech](/api/docs/api-reference/text-to-speech/generate) endpoint.

## June 16, 2026

## Falcon 2 Model Launch

We're excited to announce a major release: the new Falcon 2 model is now live, delivering significant improvements in voice quality, latency, and generation reliability.

### Improvements

* **Significantly improved voice quality**
* **Near-zero hallucinations**
* **Faster Time to First Byte (TTFB) latency**
* **Enhanced overall speech generation reliability**

### Endpoint Updates

Falcon 2 is now available on:

* [Streaming API](/api/docs/api-reference/text-to-speech/stream)
* [WebSocket API](/api/docs/api-reference/text-to-speech/stream-input)

To use Falcon 2, pass `model: falcon-2` in your API requests.

Learn more about Falcon 2 [here](/api/docs/text-to-speech-models/falcon-2).

## March 5, 2026

## Deprecation of multiNativeLocale field

We have deprecated the `multiNativeLocale` field across all Text-to-Speech (TTS) endpoints, including:

* [Non-Streaming API](/api/docs/api-reference/text-to-speech/generate)
* [Streaming API](/api/docs/api-reference/text-to-speech/stream)
* [WebSockets](/api/docs/api-reference/text-to-speech/stream-input)

The `multiNativeLocale` field has been replaced by the `locale` field. We recommend updating your integrations to use the `locale` field to ensure continued compatibility with future updates.

### What's Changed?

* **Deprecated**: `multiNativeLocale`
* **New Field**: `locale`

## Model param added to List Voices endpoint

A new optional `model` query parameter has been added to the `/v1/speech/voices` endpoint.

By default, this endpoint returns all available GEN2 voices. When you specify the `model` parameter, the response returns voices appropriate for the specified TTS model. Valid values are `FALCON` and `GEN2`.

## November 6, 2025

## New TTS Streaming Model Launch

## Falcon (Beta)

* **Sub-130ms** time-to-first-audio for instant responses
* **Multilingual speech -** Handles mixed-language sentences effortlessly, with native-like pronunciation and prosody.
* **Expressive prosody** with **99.37% pronunciation accuracy**
* **Data residency** in 11 regions via streaming & WebSocket TTS endpoints

Learn more about Falcon [here](/text-to-speech-models/falcon).

## September 19, 2025

## 14 New Languages Added to Murf API

Murf API now supports 14 additional languages, expanding its global reach and accessibility. The newly added languages are:

* **Malay**
* **Filipino**
* **Czech**
* **Finnish**
* **Thai**
* **Vietnamese**
* **French Canadian**
* **Swedish**
* **Telugu**
* **Malayalam**
* **Kannada**
* **Marathi**
* **Gujarati**
* **Punjabi**

These languages come with high-quality voices and support for advanced features like Multilingual technology and voice customization. Explore the new voices in our [Interactive Voice Explorer](https://murf.ai/api/products/text-to-speech/Falcon?utm_source=murf_api_docs) or in our [Voice Library](/api/docs/voices-styles/voice-library).

## July 29, 2025

## Enhanced Data Privacy with Zero Data Retention

We've enhanced data privacy by allowing zero data retention. By setting the `encodeAsBase64` parameter to `true`, you can receive synthesized audio as a Base64 encoded string directly in the API response, with zero data stored on Murf's servers.

This feature is designed for applications handling sensitive information, ensuring that your data is not persisted after the API call.

## July 22, 2025

## Original Text in Word Durations

A new parameter, `wordDurationsAsOriginalText`, has been added to the `/v1/speech/generate` endpoint.

By default, the `wordDurations` object in the API response contains normalized text. When you set `wordDurationsAsOriginalText` to `true`, the response will instead include the original, un-normalized text from your request. This allows for a direct mapping between your input text and the corresponding word-level timestamps.

This feature is currently available for English only.

## July 18, 2025

## Expanded Audio Format Support in TTS and Streaming

We've enhanced our audio format support for both Text-to-Speech and Streaming APIs to provide you with greater flexibility.

* The `format` parameter in the Text-to-Speech API (`/v1/speech/generate`) now accepts `PCM` and `OGG`.
* The `format` parameter in the streaming API (`/v1/speech/stream`) now accepts `PCM`.

These new options are available for immediate use.

## June 16, 2025

## WebSocket Streaming for TTS API

We are excited to launch WebSocket streaming for our Text-to-Speech API. This feature enables developers to build real-time, low-latency voice experiences by streaming text and receiving synthesized audio over a persistent, bidirectional connection. It is ideal for applications like conversational AI, live chat support, and dynamic content narration where immediate audio feedback is crucial.

Key features include:

* **Low-Latency Communication**: Stream text and receive audio with minimal delay.
* **Bidirectional Streaming**: Send text and receive audio on the same connection.
* **Efficient**: Avoids the overhead of repeated HTTP requests for continuous audio synthesis.
* **Real-Time Control**: Adjust voice style, speed, and pitch during the session.

Learn more in our [WebSocket Streaming documentation](/api/docs/text-to-speech/web-sockets).

## May 8, 2025

## New API Releases

Introducing two powerful new APIs:

### Voice Changer API

Transform your audio recordings into lifelike AI voices with advanced controls for prosody, accent retention, and more. Learn more in the [Voice Changer API Overview](/api/docs/capabilities/voice-changer).

### Translation API

Seamlessly translate text into multiple languages with high-quality results. Supports 23 languages and growing. Learn more in the [Translation API Overview](/api/docs/capabilities/translation).

## May 7, 2025

## Streaming Endpoint for TTS API

We are thrilled to introduce the **Streaming Endpoint for TTS API**, enabling developers to generate and play text-to-speech audio in real-time with minimal latency. This feature is ideal for conversational AI, live applications, and other scenarios requiring immediate audio feedback.

Learn more about the API in the [Streaming TTS API Overview](/api/docs/text-to-speech/streaming).

## April 10, 2025

## Dub Automation API Released

We are excited to announce the release of the **Murf Dub Automation API**, enabling developers to automate high-quality dubbing workflows with ease. Key features include:

* **Multi-language Support**: Create dubs in 28 languages with realistic voices.
* **Transient and Persistent Modes**: Choose between temporary, lightweight dubs or project-based, editable dubs.
* **Bulk Processing**: Upload and dub thousands of videos with rapid turnaround.
* **Enterprise-Grade Security**: Strict data handling policies with options for ephemeral storage and controlled retention periods.

Learn more about the API in the [Dub Automation API Overview](/api/docs/capabilities/dubbing).

## March 26, 2025

## 8 New Languages Added to Murf API

Murf API now supports 8 additional languages, expanding its global reach and accessibility. The newly added languages are:

* **Turkish**
* **Indonesian**
* **Japanese**
* **Croatian**
* **Greek**
* **Romanian**
* **Slovak**
* **Bulgarian**

These languages come with high-quality voices and support for advanced features like Multilingual technology and voice customization. Explore the new voices in our [Interactive Voice Explorer](https://murf.ai/api/products/text-to-speech/Falcon?utm_source=murf_api_docs) or in our [Voice Library](/api/docs/voices-styles/voice-library).

## February 13, 2025

## Official Python SDK

Murf's official python SDK is now available on PyPi. You can install it using pip:

```bash
pip install murf
```

The SDK provides a simple interface to interact with Murf's APIs. Here's an example of how you can use the SDK to generate speech:

```python
from murf import Murf

client = Murf(
    api_key="YOUR_API_KEY" # Not required if you have set the MURF_API_KEY environment variable
)

res = client.text_to_speech.generate(
    text="There is much to be said",
    voice_id="terrell",
)
```