#text-to-speech

[ follow ]
#openai
Artificial intelligence
fromInfoQ
3 months ago

OpenAI Introduces New Speech Models for Transcription and Voice Generation

OpenAI's new models improve speech transcription accuracy and flexibility in AI-generated voice adaptation.
Artificial intelligence
fromInfoQ
3 months ago

OpenAI Introduces New Speech Models for Transcription and Voice Generation

OpenAI's new models improve speech transcription accuracy and flexibility in AI-generated voice adaptation.
more#openai
#mobile-app
fromZDNET
10 months ago
Digital life

ElevenLabs' Reader app can read anything aloud to you - now in 32 languages - for free

fromZDNET
10 months ago
Digital life

ElevenLabs' Reader app can read anything aloud to you - now in 32 languages - for free

more#mobile-app
Artificial intelligence
fromZDNET
3 weeks ago

Text-to-speech with feeling - this new AI model does everything but shed a tear

ElevenLabs introduces v3, the most expressive text-to-speech technology, boasting enhanced human-like emotional expression.
fromGadgets 360
1 month ago

Switch 2 Will Support Text-to-Speech, VRR Will Be Limited to Handheld Mode

Text-to-speech functionality can be seen in a gameplay video showing off the new GameChat feature, where users can type messages and the system reads them out.
Video games
Artificial intelligence
fromeLearning
1 month ago

Creating Natural Narration with Adobe Captivate's Text-to-Speech using AI voices - eLearning

Adobe Captivate's new AI text-to-speech feature streamlines voiceover creation for eLearning courses.
#ai
Artificial intelligence
fromZDNET
4 months ago

This new text-to-speech AI model understands what it's saying - how to try it for free

Hume's Octave is a text-to-speech AI that uses contextual awareness to produce more natural-sounding speech.
Octave allows users to define emotional tones and create unique voices.
NYC startup
fromTechCrunch
4 months ago

Podcasting platform Podcastle launches a text-to-speech model with more than 450 AI voices | TechCrunch

Podcastle has launched Asyncflow v1.0, a low-cost AI text-to-speech model offering over 450 voices, enhancing their podcast platform.
Artificial intelligence
fromZDNET
4 months ago

This new text-to-speech AI model understands what it's saying - how to try it for free

Hume's Octave is a text-to-speech AI that uses contextual awareness to produce more natural-sounding speech.
Octave allows users to define emotional tones and create unique voices.
NYC startup
fromTechCrunch
4 months ago

Podcasting platform Podcastle launches a text-to-speech model with more than 450 AI voices | TechCrunch

Podcastle has launched Asyncflow v1.0, a low-cost AI text-to-speech model offering over 450 voices, enhancing their podcast platform.
more#ai
fromHackernoon
6 months ago

How We Used the LibriTTS Dataset to Train the Hierarchical Speech Synthesizer | HackerNoon

We utilized the LibriTTS dataset to train the hierarchical speech synthesizer, specifically using the train-clean subsets for fair model comparisons while enhancing voice style transfer.
Data science
[ Load more ]