#text-to-speech

[ follow ]
#speech-to-text
Artificial intelligence
fromInfoQ
1 month 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
1 month 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#speech-to-text
#ai
NYC startup
fromTechCrunch
1 month 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.
fromTheregister
2 months ago
Artificial intelligence

Zypher's speech model can clone your voice with 5s of audio

Zyphra's new TTS models can clone voices using just five seconds of audio.
NYC startup
fromTechCrunch
1 month 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.
fromTheregister
2 months ago
Artificial intelligence

Zypher's speech model can clone your voice with 5s of audio

Zyphra's new TTS models can clone voices using just five seconds of audio.
more#ai
fromAdobe
3 months ago
Django

Text to speech options | eLearning

Captivate 12's Text to Speech voices can sound robotic, making external voiceover options seem more appealing despite potential syncing challenges.
#speech-synthesis
fromHackernoon
4 months ago
Data science

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

The paper discusses training a hierarchical speech synthesizer using the LibriTTS dataset, emphasizing the importance of data diversity for robust voice style transfer.
fromHackernoon
1 year ago
Miscellaneous

HierSpeech++: How Does It Compare to Vall-E, Natural Speech 2, and StyleTTS2? | HackerNoon

The Hierspeech++ model outperforms existing models in naturalness and prompt similarity for zero-shot speech synthesis.
The evaluation revealed important limitations in similarity with ground truth versus prompt-generated speech.
fromHackernoon
4 months ago
Data science

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

The paper discusses training a hierarchical speech synthesizer using the LibriTTS dataset, emphasizing the importance of data diversity for robust voice style transfer.
fromHackernoon
1 year ago
Miscellaneous

HierSpeech++: How Does It Compare to Vall-E, Natural Speech 2, and StyleTTS2? | HackerNoon

The Hierspeech++ model outperforms existing models in naturalness and prompt similarity for zero-shot speech synthesis.
The evaluation revealed important limitations in similarity with ground truth versus prompt-generated speech.
more#speech-synthesis
JavaScript
fromMedium
5 months ago

Building AI Workflows: Combining LLMs and Voice Models-Part 1

Building an AI podcast requires combining LLMs for scripting and text-to-speech models to create autonomous audio content.
fromCodeProject
10 years ago
JavaScript

Computer Talker with C#

The program enables text-to-speech functionality using the SpeechSynthesizer class in a Windows Forms application.
JavaScript
fromCodeProject
8 months ago

Complete Voice Interaction with ChatGPT

The project effectively combines speech recognition and TTS to facilitate uninterrupted interaction with ChatGPT, enhancing user experience.
fromZDNET
8 months ago
Digital life

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

ElevenLabs expands its Reader app globally, supporting 32 languages and featuring various voices, including celebrities, with improved text-to-speech technology.
fromFlowingData
11 months ago
Marketing

Welcome to the future of data reporting, in musical format

The TikTok account Globetrots creatively combines Google Earth and text-to-speech for engaging top-ten list videos.
[ Load more ]