ElevenLabs, a prominent player in the text-to-speech domain with a strong focus on artificial intelligence (AI), has unveiled a groundbreaking AI solution aimed at simplifying the creation of distinctive audiobooks, LiveWire reported. Known as Projects, this platform streamlines the production process for generating long-form spoken content, particularly audiobooks. Leveraging the company’s advanced AI-driven voice technology platform, Projects offers a range of innovative features.
The core technology behind Projects allows for the conversion of any text into speech using synthetic voices, cloned voices, or the creation of entirely novel artificial voices, which can be fine-tuned based on specific attributes such as gender, age, and accent. ElevenLabs asserts that their proprietary AI models are capable of generating the most versatile and contextually-aware voices, making them ideal for the audiobook format. By employing realism-based algorithms and achieving a remarkable latency of less than 1 second, the resulting audio content is claimed to be virtually indistinguishable from that of a human narrator. The service is scheduled for launch in July, but an early access version is currently available, presenting an opportunity to embark on the creation of a remarkable audio novel.
In addition to Projects, ElevenLabs has introduced another significant offering—an audio analysis service designed to detect the presence of AI-generated speech within spoken word audio. This tool allows users to upload any audio sample for inspection, enabling transparency in identifying AI-generated speech. This represents a significant stride towards ElevenLabs’ commitment to openness and accountability in the realm of AI-driven speech synthesis.
Projects and the aforementioned audio analysis tool complement ElevenLabs’ existing suite of text-to-speech solutions, which includes Speech Synthesis, a powerful platform for transforming text into speech, and VoiceLab, a tool facilitating the digital replication of existing voices. Moreover, with the recent introduction of Eleven Multilingual service, these offerings are now available not only in English but also in major European languages, amplifying their accessibility and usability on a global scale.
With a keen interest in tech, I make it a point to keep myself updated on the latest developments in technology and gadgets. That includes smartphones or tablet devices but stretches to even AI and self-driven automobiles, the latter being my latest fad. Besides writing, I like watching videos, reading, listening to music, or experimenting with different recipes. The motion picture is another aspect that interests me a lot, and I'll likely make a film sometime in the future.