News from the AI & ML world
DeeperML
@www.producthunt.com
//
ElevenLabs has launched Eleven v3, its most expressive text-to-speech model to date. The new system is designed to handle reactions, interruptions, and a range of emotions more naturally than previous versions. ElevenLabs aims to position Eleven v3 as the most expressive AI voice on the market, equipped with audio tags, support for over 70 languages, and a dialogue function. The model is available as an alpha version through the company’s website.
ElevenLabs rebuilt the model from scratch to enable voices that can whisper, laugh, sigh, or react with surprise. Users can control expressive cues using audio tags embedded directly in the text, such as "[sighs]" or "[excited]." Combinations of tags are supported for nuanced delivery, such as "We did it! [happily][shouts] [laughs]." The company sees v3 as an experimental tool for developers and media creators looking to push the limits of AI-generated speech, with support for over 70 languages intended for professional applications such as film, audiobook production, and digital media.
One of the standout features is support for multispeaker dialogues with realistic conversational flow, facilitated by a new text-to-dialogue API. This API allows users to send structured JSON objects defining each speaker's turn, enabling the model to automatically manage speaker changes, emotional shifts, and even interruptions. Text processing has also been improved, aiming for better alignment of emphasis, cadence, and speech melody with the meaning of the text, enhancing the realism and expressiveness of AI-generated speech.
ImgSrc: ph-files.imgix.
References :
ElevenLabs rebuilt the model from scratch to enable voices that can whisper, laugh, sigh, or react with surprise. Users can control expressive cues using audio tags embedded directly in the text, such as "[sighs]" or "[excited]." Combinations of tags are supported for nuanced delivery, such as "We did it! [happily][shouts] [laughs]." The company sees v3 as an experimental tool for developers and media creators looking to push the limits of AI-generated speech, with support for over 70 languages intended for professional applications such as film, audiobook production, and digital media.
One of the standout features is support for multispeaker dialogues with realistic conversational flow, facilitated by a new text-to-dialogue API. This API allows users to send structured JSON objects defining each speaker's turn, enabling the model to automatically manage speaker changes, emotional shifts, and even interruptions. Text processing has also been improved, aiming for better alignment of emphasis, cadence, and speech melody with the meaning of the text, enhancing the realism and expressiveness of AI-generated speech.
ImgSrc: ph-files.imgix.
Share:
References :
- analyticsindiamag.com: ElevenLabs Unveils ‘v3’, Its Most Expressive Text-to-Speech Model Yet
- the-decoder.com: Elevenlabs' Eleven v3 lets AI voices whisper, laugh and express emotions naturally
- www.producthunt.com: The most expressive Text to Speech model ever |
Classification:
- HashTags: #AI #TTS #ElevenLabs
- Company: ElevenLabs
- Target: Content Creators
- Product: Eleven v3
- Feature: Text-to-Speech
- Type: AI
- Severity: Informative