Introducing a Revolutionary AI Model that Generates Ultra-Realistic Voices in Over 20 Languages

Voice generation platform Murf AI has unveiled its latest innovation: the Murf Speech Gen 2, a powerful text-to-speech model designed to produce highly customizable and emotive audio outputs. This new model is engineered to deliver broadcast-quality audio that mirrors the nuances of human speech, making it an exceptional tool for a variety of applications such as marketing collateral and corporate training materials.

One of the standout features of Murf Speech Gen 2 is its remarkable pronunciation accuracy, achieving a near-perfect rate of 98.8% for general American English. Beyond English, the model offers multilingual support, generating audio in over 20 languages, thus catering to a global audience and broadening its applicability across different markets.

"We believe the launch of Murf Speech Gen 2 marks a transformative phase for our company," stated Ankur Edkie, co-founder and CEO of Murf AI. "This model stands as a testament to our dedication to innovation, designed to empower enterprises with cutting-edge AI tools that maximize their creative capabilities."

In an increasingly competitive landscape that includes well-known platforms like ElevenLabs, Lovo, and Speechify, Murf distinguishes itself with features such as the ability to create more than 120 distinct voice clones. Additionally, the "Say it My Way" feature allows users to upload their own voice recordings, enabling the AI to generate a voice clone that replicates their unique speech patterns. This level of customization extends to pronunciation control, giving users the ability to emphasize or de-emphasize specific phonetic details in the final audio output.

To develop the Murf Speech Gen 2 model, researchers utilized over 70,000 hours of diverse speech data from an array of speakers. This extensive training empowers the model to produce audio across the full range of human audible frequencies. Furthermore, the model incorporates what the company calls a “deep linguistic modeling layer,” which enhances its ability to capture complex accentual nuances in multiple languages.

Murf has also introduced Murf Dub, a novel dubbing tool designed to facilitate the creation of multilingual audio content. This tool enables users to efficiently adapt video materials into various languages, making it easier to translate social media assets for different cultural contexts. Currently, Murf Dub supports seven languages: English, Spanish, Italian, German, French, Hindi, and Portuguese.

"As we advance, our goal at Murf AI is to collaborate with creators, bridging the gap between visionary ideas and their execution," added Edkie. "We are continually striving to innovate beyond traditional voiceovers, prioritizing both control and versatility for our users. By setting a new standard in the industry, we empower creators to achieve their desired output exactly as they envision it."