Latest news with #ElevenLabs
Geeky Gadgets
3 hours ago
- Entertainment
- Geeky Gadgets
Introducing Voice Design v3 from Eleven Labs to Create Expressive AI Voices from Text
What if you could craft a voice that feels as real as a conversation with a close friend—or as otherworldly as a character from your wildest imagination—using nothing more than a few descriptive words? With the release of Voice Design v3, Eleven Labs is redefining what's possible in the realm of AI voice synthesis. This innovative tool doesn't just generate voices; it creates deeply expressive, lifelike audio tailored to your exact needs. Whether you're a filmmaker seeking an emotionally resonant narrator or a game developer designing immersive character dialogue, Voice Design v3 offers an unprecedented level of customization and creative freedom. It's not just a tool—it's a gateway to reimagining how stories are told. ElevenLabs reveals the new features that set Voice Design v3 apart, from its ability to interpret nuanced text descriptions to its seamless adaptability across industries like gaming, filmmaking, and podcasting. You'll discover how this platform enables creators to design voices that don't just speak but truly connect with audiences. By blending advanced AI technology with an intuitive interface, Eleven Labs has made it easier than ever to push the boundaries of audio storytelling. Could this be the future of voice design? Let's examine how this innovation is reshaping the soundscape of creative projects. Create Custom AI Voices What Sets Voice Design v3 Apart? Voice Design v3 stands out due to its sophisticated AI model, which generates highly realistic and expressive voices. Using advanced text-to-speech (TTS) technology, this tool allows you to craft unique voice profiles tailored to your specific creative needs. Whether you require a voice that conveys authority, warmth, or even an otherworldly quality, the system adapts with remarkable precision to your vision. The platform's ability to interpret nuanced descriptions and translate them into lifelike voice models is a key feature. By focusing on flexibility and precision, Voice Design v3 enables you to explore a wide spectrum of vocal styles, making sure that your project's audio elements align seamlessly with its overall tone and purpose. How Custom Voice Modeling Works Voice Design v3 simplifies the traditionally complex process of voice synthesis. Unlike conventional tools that depend on pre-recorded samples, this platform allows you to describe the desired voice characteristics in detail. You can specify attributes such as pitch, tone, emotional depth, and even subtle vocal nuances. The AI then generates a voice model that aligns with your description, offering unparalleled customization. This approach not only saves time but also provides the creative freedom to experiment with diverse vocal styles. Whether you're designing a voice for a commanding narrator, a whimsical character, or a deeply emotional storyteller, the tool adapts to your requirements, making sure a perfect fit for your project. What is Voice Design v3? Discover Eleven Labs' AI Voice Revolution Watch this video on YouTube. Enhance your knowledge on AI voice generation by exploring a selection of articles and guides on the subject. Applications Across Creative Industries Voice Design v3 is a versatile tool with applications spanning multiple creative fields. Its ability to generate tailored voice models makes it an invaluable resource for enhancing various types of projects. Here are some key areas where this technology can make a significant impact: Filmmaking: Create distinct character voices that add depth and authenticity to your narrative, enhancing the emotional resonance of your story. Create distinct character voices that add depth and authenticity to your narrative, enhancing the emotional resonance of your story. Video Games: Design immersive in-game experiences by crafting voices that reflect the unique personalities and backstories of characters. Design immersive in-game experiences by crafting voices that reflect the unique personalities and backstories of characters. Storytelling: Bring stories to life with voices that captivate audiences and evoke a wide range of emotions. Bring stories to life with voices that captivate audiences and evoke a wide range of emotions. Corporate Training: Develop professional voiceovers for instructional videos, making sure clarity and engagement. Develop professional voiceovers for instructional videos, making sure clarity and engagement. Podcasts and Audiobooks: Produce high-quality audio content with voices that match the tone and theme of your material. The adaptability of Voice Design v3 ensures that it can meet the diverse needs of creative professionals, regardless of the medium or genre they are working in. Versatility and Adaptability for Creative Projects One of the most compelling features of Voice Design v3 is its ability to produce a wide range of voices, from professional and authoritative to imaginative and surreal. This versatility ensures that the tool can cater to a variety of creative demands. Whether you're working on a corporate training video, an animated series, or a podcast, the AI-generated voices seamlessly adapt to the tone and context of your project. The platform's intuitive interface further enhances its usability, allowing you to fine-tune vocal expressions and characteristics with ease. This level of customization opens up new possibilities for experimenting with sound, allowing you to push the boundaries of audio storytelling and design. Redefining the Future of Expressive Voice Synthesis Voice Design v3 represents a significant step forward in the evolution of AI voice technology. By combining advanced algorithms with an intuitive user experience, Eleven Labs has created a platform that enables you to bring your creative ideas to life with precision and ease. The tool's ability to generate expressive, custom voice models based on user descriptions sets a new benchmark for what's possible in voice synthesis. As the demand for dynamic and engaging audio content continues to grow, tools like Voice Design v3 are shaping the future of creative audio design. Whether you're a filmmaker, game developer, or content creator, this technology offers a powerful way to enhance your projects and connect with audiences on a deeper level. Elevating Creative Storytelling Through Innovation Voice Design v3 from Eleven Labs is more than just a text-to-speech tool—it's a comprehensive platform for creative audio design. Its ability to generate lifelike, customizable voices makes it an indispensable resource for professionals seeking to elevate their storytelling and design projects. By harnessing the power of this advanced AI technology, you can ensure that your work resonates with audiences in impactful and memorable ways. Media Credit: ElevenLabs Filed Under: AI, Technology News, Top News Latest Geeky Gadgets Deals Disclosure: Some of our articles include affiliate links. If you buy something through one of these links, Geeky Gadgets may earn an affiliate commission. Learn about our Disclosure Policy.
CBC
a day ago
- Health
- CBC
How an AI cloning tool is letting this Quebec man with ALS keep his voice
Leaning into a small microphone in a Quebec City studio, Dr. Alec Cooper takes a breath and reads out part of the often-quoted "To be, or not to be" soliloquy from Shakespeare's Hamlet. "It's pretty dramatic," said Cooper, backing away from the microphone and letting out a laugh. "I just realized, my God, it really is talking about death." It's a subject Cooper says he's been forced to think about over the past year and a half after he was diagnosed with ALS, a terminal motor neuron disease. He was initially given an average life expectancy of two to five years. The family doctor, originally from Victoria, had 1,800 patients before announcing his snap retirement last year. Staying busy renovating his house to become wheelchair accessible, Cooper has also been spending more time in front of a microphone — recording common sayings, elaborate poems and his favourite book passages as part of the process to clone his voice for when the disease progresses further. He's using AI-powered voice technology by ElevenLabs — a U.S.-based company that is offering the tech to one million people who suffer from degenerative diseases, including ALS, mouth cancer, stroke victims or those with Parkinson's disease. The AI tool allows users to input a small amount of audio which generates a voice clone with that person's natural tone and inflection when they need to rely on text-to-speech devices. Cooper started feeding the ElevenLabs bank himself at home and is getting help from professionals at the local rehab centre. "When the voice is gone, it's gone forever," said Cooper. "Thanks to this technology, the disease can't take my voice away." 'Facing it with tremendous courage' Compared to most people who have an ALS diagnosis, Cooper says he's considered a "slow progressor" and that he looks "pretty bloody good." Still, the symptoms of the illness are creeping up. He says he's starting to have trouble dressing, doing up buttons and handling utensils. His friend, Dr. Jean-Pierre Canuel, who was diagnosed with ALS 11 years ago, is further along. Canuel, a retired doctor, still gardens using his lawn mower, drives an adapted van and is dedicated to his hobby of making wooden charcuterie boards. Sitting in his motorized wheelchair, he smiles while swiping through photos of his grandchildren. It takes great effort to speak, but Canuel tells CBC that before his diagnosis, "I was a strong man." He did not have the opportunity to record his voice before his speech became severely impacted by the disease. Canuel burst into tears as Cooper greeted him in the recording area in Quebec City on a humid morning at the end of June. "It's taken his voice away, which happens to all of us," said Cooper, resting his hand on Canuel's back, consoling him. "He's facing it with tremendous courage." It's an approach Cooper is trying to adopt, he says, taking all the advice and inspiration from Canuel as possible. "I'll get all misty-eyed again, but Jean-Pierre is an incredibly courageous person. That's the way I want to be," he said, breaking down. "You have to kind of embrace it and not deny it." Improving quality of life AI voice cloning is relatively new, says Dr. Angela Genge, head of the ALS Centre of Excellence at the Montreal Neurological Institute. She says until the past decade, it wasn't widely available to patients. But multidisciplinary clinics can now offer patients voice banking relatively early on in their diagnosis, she says. WATCH | 'He has a great sense of humour' says wife of man with ALS: Meet the man using AI to clone his voice before he loses it to ALS 3 minutes ago Duration 3:25 "It makes a big difference for them," said Genge, a professor at McGill University. "I see AI helping with quality of life and I think it's fairly significant." She says she's used to hearing computer-generated voices articulating what patients want to say. Before the "computer age," she says patients were limited to talking using pointing cards. Now, when the disease progresses to the point of impacting speech, a patient can be equipped with devices which can formulate words and sentences in their own voice, says Sophie Dupont, a speech language pathologist for the local health authority working at the Institut de réadaptation en déficience physique de Québec. " When we're talking about text, you're literally going to be typing first [on a tablet] if you are still able," she said. The tool can also be adjusted to be used through eye control or head tracking, much like the speech-generating device used by renowned physicist Stephen Hawking, who had ALS, Dupont says. Usually, when patients arrive in her office, their ability to speak is already impaired, she says. In these cases, she relies on recordings or voicemails to power an AI voice. Having worked with Cooper for the past six months, Dupont says the AI tool is used on an exceptional basis. She says she has to balance the urgency of patients' needs with current resources. 'It's going to be a legacy' Traditionally, robotic voices available for ALS patients didn't come in all shapes and sizes, says Dustin Blank, based in Los Angeles, who leads partnerships at ElevenLabs. "Now every dialect, every language … it sounds like yourself," he said. "It is how they spoke in that same cadence, in that same emotion. And that's super powerful." He says the company's impact program is hoping to find ways to get their voice technology into the hands of people who need it most. With concerns regarding the power and security of AI, he says the company understands that voices, and the process of cloning them, are "powerful things." Taking steps to protect people's voices with password protection and voice verification, the company takes safety "very seriously," he says. Sylvie Barma, Cooper's wife of 30 years, says this tool is proof that AI is "not only bad things." While her husband is enjoying the process of using the AI tool, for Barma, the recording process is a reminder of the reality of the disease and the challenges the couple is bound to face as Cooper's health deteriorates. When she overhears him recording at home, Barma says she steps out into her sanctuary — her garden. "I just move away," she says. "We know it's coming, but I prefer not to think too much ahead.
Mint
6 days ago
- Business
- Mint
ElevenLabs expands access to AI voice tools with iOS and Android app: Features, availability and more
ElevenLabs, a voice AI company, has announced the launch of its first-ever mobile app for iOS and Android. The company claims the app will make its powerful voice tools more accessible to users worldwide. The new app offers mobile access to the firm's advanced text-to-speech technology, including its latest Eleven v3 model, known for its expressive, lifelike voice generation. Available now via the App Store and Google Play, the app allows creators to produce high-quality voiceovers on the move, removing the need for desktop setups and enabling faster, more flexible content creation. The mobile app retains the core features of ElevenLabs' web platform, allowing users to generate speech with selected voices and presets, export audio clips for use in editing apps like CapCut and InShot, and sync projects seamlessly with their existing ElevenLabs account. New users start with a monthly allowance of 10,000 free characters, while existing customers can access their full subscription benefits directly through the app. The launch is in response to growing demand from content creators, educators, marketers, and professionals who have been accessing ElevenLabs through mobile browsers. With many users seeking a more streamlined and performance-optimised experience, the app marks a significant upgrade in usability and creative flexibility. 'At the heart of this launch is our most advanced speech model yet,' the company said, referring to the Eleven v3 engine. The model offers nuanced control over tone, pacing, and emotion, enabling users to fine-tune the delivery to suit their storytelling needs, whether that is for videos, narration, or social media content. ElevenLabs says the release is part of its broader mission to make content creation truly borderless, 'any voice, any language, anywhere'. As the app continues to evolve, the company plans to expand functionality and language support to empower creators across the globe. The mobile app is available for free download now, with premium features available through ElevenLabs' existing credit-based plans.
Hindustan Times
6 days ago
- Hindustan Times
ElevenLabs launches mobile app: Brings powerful AI text to speech to smartphones
Jun 25, 2025 06:08 PM IST ElevenLabs released an app for Android and iOS, bringing its AI-powered text-to-speech feature to smartphones. It offers a large selection of native AI voice models to choose from and generate content. This app is available for both free and premium users and comes with a very clean user interface. Here's everything you need to know about the app and how to use it to convert text to voice for your projects. ElevenLabs brings AI voice creation to your mobile.(ElevenLabs) The ElevenLabs app brings its best text-to-speech model, Eleven v3, to smartphones. This new model supports up to 70 languages and multiple speaker dialogues. It also supports multiple audio tags such as whisper, excited, and sighs. It delivers very realistic speech and emotions, making it a handy tool for content creators, educators, and more who are seeking a rich and accurate text-to-speech app. Download the ElevenLabs app from the App Store or the Play Store. Open the app, and you will see a text box on the main screen. Paste your text or type it in the text box. Tap the voice selection in the bottom right to change the voice. You can change settings like the AI model, speed, stability, and more. Finally, hit generate to create the speech. You can see the amount of credits it will consume before generating the voice, so you can manage your credits better. Generated speech can be saved to the device or shared on social media or messaging apps. ElevenLabs pricing ElevenLabs offers 10,000 free credits every month to users' accounts. This is enough to generate 10 minutes of AI voice. These credits are shared across the website and can be used from either platform. Other than text-to-speech, these credits can also be used for speech-to-text, automated dubbing, API access, and more. Paid subscriptions start from $1 a month, which triples the amount of credits in free mode.
Time of India
7 days ago
- Business
- Time of India
ElevenLabs powers voice for Cisco's Webex AI agent
Bringing voice-first, agentic customer support to the enterprise. We're thrilled that ElevenLabs is now powering the voice technology behind the Webex AI Agent . At ElevenLabs, we believe that natural, expressive voice should be the standard for all AI agents. Expressive voices keep customers engaged throughout conversations, allowing agents to deliver meaningful results and create genuine value. We're proud to partner with an industry leader like Cisco to make this vision a reality, bringing voice-first, agentic customer support to the enterprise. Addressing a critical customer experience gap Recent research from Cisco has revealed major gaps between consumer expectations and reality in today's customer service landscape: • Only 25% of customers report being "very satisfied" with their last customer service engagement. • 94% have abandoned interactions due to poor experiences. • 95% would switch brands due to sub-par customer service. The three biggest frustrations? Having to repeatedly explain their issue (54%), dealing with voice or chatbots that aren't intelligent enough to help (48%), and being kept on hold too long (31%). Beyond traditional chatbots Traditional chatbots have often frustrated customers with rigid experiences and an inability to interpret natural language. Webex AI Agent uses large language models (LLMs) to deliver more human-like customer experiences that understand an individual's needs, remember their history, and adapt to their preferences. By integrating ElevenLabs' voice technology, Webex AI Agent can deliver voice interactions that sound and feel like conversing with a real person—thanks to the agent's human-like intonation, inflections and rhythm. What's more, its voice AI can respond to a customer's emotional cues and adapt its delivery — sounding warm and welcoming when needed, or serious and empathetic when the situation calls for it. This new partnership addresses the evolving needs of enterprises by combining advanced voice technology with Cisco's scalable channel support and intuitive design tools — enabling seamless integration with custom knowledge bases and critical backend systems such as CRM, ERP, and HR platforms. Meet the all-new Webex AI Agent 'At Cisco, we're focused on delivering AI-powered customer experiences that are natural, responsive, and scalable,' says Jay Patel, Senior Vice President and General Manager fo Webex Customer Experience Solutions. 'Voice plays a critical role in humanizing these interactions, and ElevenLabs' text-to speech technology has helped us bring greater nuance and clarity to our AI agents. It's a valuable component in our broader strategy to make customer engagement more intuitive and effective. Together, we're delivering human-sounding AI with enterprise grade performance, security and scalability.' 'Our mission is to make AI sound more like us - empathetic, dynamic, real,' adds Mati Staniszewski, CEO and Co-founder of ElevenLabs. 'By joining forces with Cisco, we're ensuring that our innovative technology can meet the complex demands of any enterprise environment, by bridging the gap between life-like AI interactions and the enterprise infrastructure required to deliver them at scale.' As businesses continue to explore the possibilities of AI-powered customer support , the partnership between ElevenLabs and Cisco serves as a powerful example of how voice technology can create more human digital experiences. We're excited to see how Webex AI Agent transforms customer support operations worldwide and look forward to continuing our collaboration with Cisco on future innovations. Cisco Confidential
