#VoiceTechnology

2025-05-23

๐ŸŒŸ Excited to share Thorsten-Voice's YouTube channel! ๐ŸŽฅ ๐Ÿ—ฃ๏ธ๐Ÿ”Š โ™ฟ ๐Ÿ’ฌ

Thorsten presents innovative TTS solutions and a variety of voice technologies, making it an excellent starting point for anyone interested in open-source text-to-speech. Whether you're a developer, accessibility advocate, or tech enthusiast, his channel offers valuable insights and resources. Don't miss out on this fantastic content! ๐ŸŽฌ

follow hem here: @thorstenvoice
or on YouTube: youtube.com/@ThorstenMueller YouTube channel!

#Accessibility #FLOSS #TTS #ParlerTTS #OpenSource #VoiceTech #TextToSpeech #AI #CoquiAI #VoiceAssistant #Sprachassistent #MachineLearning #AccessibilityMatters #FLOSS #TTS #OpenSource #Inclusivity #FOSS #Coqui #AI #CoquiAI #VoiceAssistant #Sprachassistent #VoiceTechnology #KรผnstlicheStimme #MachineLearning #Python #Rhasspy #TextToSpeech #VoiceTech #STT #SpeechSynthesis #SpeechRecognition #Sprachsynthese #ArtificialVoice #VoiceCloning #Spracherkennung #CoquiTTS #voice #a11y #ScreenReader

Interservinterserv
2025-04-15

During the makings of our Introduction to DaVinci Series, we tried both AI and traditional narration. Here are our observations.

interserv.com.au/blog/our-expe

Hacker Newsh4ckernews
2025-04-09
2025-03-22

๐ŸŽ™๏ธ OpenAI presenta i nuovi modelli audio nella sua API, per speech-to-text e text-to-speech.
๐Ÿ‘‰ Una sintesi dei dettagli: linkedin.com/posts/alessiopoma

___ 

โœ‰๏ธ ๐—ฆ๐—ฒ ๐˜ƒ๐˜‚๐—ผ๐—ถ ๐—ฟ๐—ถ๐—บ๐—ฎ๐—ป๐—ฒ๐—ฟ๐—ฒ ๐—ฎ๐—ด๐—ด๐—ถ๐—ผ๐—ฟ๐—ป๐—ฎ๐˜๐—ผ/๐—ฎ ๐˜€๐˜‚ ๐—พ๐˜‚๐—ฒ๐˜€๐˜๐—ฒ ๐˜๐—ฒ๐—บ๐—ฎ๐˜๐—ถ๐—ฐ๐—ต๐—ฒ, ๐—ถ๐˜€๐—ฐ๐—ฟ๐—ถ๐˜ƒ๐—ถ๐˜๐—ถ ๐—ฎ๐—น๐—น๐—ฎ ๐—บ๐—ถ๐—ฎ ๐—ป๐—ฒ๐˜„๐˜€๐—น๐—ฒ๐˜๐˜๐—ฒ๐—ฟ: bit.ly/newsletter-alessiopomar 

#AI #GenAI #GenerativeAI #IntelligenzaArtificiale #LLM #voicetechnology

I nuovi modelli TTS e STT di OpenAII nuovi modelli TTS e STT di OpenAII nuovi modelli TTS e STT di OpenAI
2025-03-02

๐Ÿง  #Amazon lancia la nuova generazione di #Alexa, potenziata dall'#AI generativa.
๐Ÿ—ฃ๏ธ Alexa+ comprende linguaggio naturale, puรฒ gestire la casa smart, fare prenotazioni, suggerire contenuti e navigare autonomamente sul web per completare attivitร . 

___ 

โœ‰๏ธ ๐—ฆ๐—ฒ ๐˜ƒ๐˜‚๐—ผ๐—ถ ๐—ฟ๐—ถ๐—บ๐—ฎ๐—ป๐—ฒ๐—ฟ๐—ฒ ๐—ฎ๐—ด๐—ด๐—ถ๐—ผ๐—ฟ๐—ป๐—ฎ๐˜๐—ผ/๐—ฎ ๐˜€๐˜‚ ๐—พ๐˜‚๐—ฒ๐˜€๐˜๐—ฒ ๐˜๐—ฒ๐—บ๐—ฎ๐˜๐—ถ๐—ฐ๐—ต๐—ฒ, ๐—ถ๐˜€๐—ฐ๐—ฟ๐—ถ๐˜ƒ๐—ถ๐˜๐—ถ ๐—ฎ๐—น๐—น๐—ฎ ๐—บ๐—ถ๐—ฎ ๐—ป๐—ฒ๐˜„๐˜€๐—น๐—ฒ๐˜๐˜๐—ฒ๐—ฟ: bit.ly/newsletter-alessiopomar 

#AI #GenAI #GenerativeAI #IntelligenzaArtificiale #VoiceTechnology

2024-12-28

โœ‰๏ธ ๐—ฆ๐—ฒ ๐˜ƒ๐˜‚๐—ผ๐—ถ ๐—ฟ๐—ถ๐—บ๐—ฎ๐—ป๐—ฒ๐—ฟ๐—ฒ ๐—ฎ๐—ด๐—ด๐—ถ๐—ผ๐—ฟ๐—ป๐—ฎ๐˜๐—ผ/๐—ฎ ๐˜€๐˜‚ ๐—พ๐˜‚๐—ฒ๐˜€๐˜๐—ฒ ๐˜๐—ฒ๐—บ๐—ฎ๐˜๐—ถ๐—ฐ๐—ต๐—ฒ, ๐—ถ๐˜€๐—ฐ๐—ฟ๐—ถ๐˜ƒ๐—ถ๐˜๐—ถ ๐—ฎ๐—น๐—น๐—ฎ ๐—บ๐—ถ๐—ฎ ๐—ป๐—ฒ๐˜„๐˜€๐—น๐—ฒ๐˜๐˜๐—ฒ๐—ฟ: bit.ly/newsletter-alessiopomar 

#AI #GenAI #GenerativeAI #IntelligenzaArtificiale #LLM #VoiceTechnology 

2024-12-28

๐Ÿง  #OCTAVE รจ un nuovo modello avanzato in grado di generare voci e personalitร  in tempo reale partendo da semplici descrizioni o registrazioni di appena 5 secondi. 
โœจ Le personalitร  create includono tratti come linguaggio, accento, espressioni, e disposizioni emotive. Puรฒ anche gestire interazioni tra piรน personalitร  e voci simultaneamente, offrendo un'interazione realistica. 

๐Ÿ”— hume.ai/blog/introducing-octav 

#AI #GenerativeAI #IntelligenzaArtificiale #VoiceTechnology 

youtube.com/watch?v=betkiRw9MD

2024-10-25

Just dropped a new video! ๐Ÿ”Š
I had the chance to present at the Washington Council of the Blind and shared how OpenAI's Advanced Voice Mode can transform the way we teach JAWS, manage daily tasks, and even prepare for job interviews!
๐ŸŽฅ Watch the full video here: youtube.com/watch?v=DVCvveNqFc
Letโ€™s talk about how AI is changing accessibility! Drop your thoughts in the comments ๐Ÿ‘‡
#Accessibility #OpenAI #AdvancedVoiceMode #JAWS #AssistiveTech #VoiceTechnology #MockInterview #WashingtonCouncilOfTheBlind

2024-10-20

๐ŸŽ‰ Celebrating 5 Years of Thorsten-Voice! ๐ŸŽ™๏ธ

As a birthday gift to the #FOSS speech community, I'm releasing all voice datasets in their original 44kHz quality (upgraded from 22kHz):

โœจ What's included:
โ€ข Neutral voice dataset
โ€ข Emotional voice dataset
โ€ข Hessisch dialect dataset

All consolidated on @huggingface fully structured & transcribed. Same CC0 license, better quality!

Perfect for #TTS development, #speech research, and #AI projects.

Get the high-quality datasets here: huggingface.co/datasets/Thorst

#OpenSource #OpenData #FLOSS #TextToSpeech #MachineLearning #GermanTTS #AI #VoiceTechnology

Showing www.Thorsten-Voice.de logo with header text "Celebrating 5 years" and a small note saying "Est. october 2019"
2024-10-11

At Pebble, weโ€™re excited to see how OpenAIโ€™s real-time voice API is pushing voice technology forward. Real-time, adaptive AI interactions are transforming healthcare, automation, and more. Weโ€™re looking forward to integrating this with our XIoT and cybersecurity solutions.

Full post from Stuart: zurl.co/4Qm6

DigiProductzdigiproductz
2024-10-03

VoizHub AI Review - Clone Any Celebrity Voice ๐ŸŽค, Dub Any Video or Voice In Any Language ๐ŸŒ, Record In Real-Time ๐ŸŽ™๏ธ, AI Transcript Anything ๐Ÿ“, Turn Any Text Into Speech ๐Ÿ—ฃ๏ธ, Turn Any URL Into Speech ๐ŸŒ, Generate Podcasts ๐ŸŽง, Narrate Audiobooks ๐Ÿ“š, Narrate Short Videos ๐ŸŽฅ, And More โœจ!

Get Instant Access: digiproductz.com/get/voizhub-ai
Read Full Review: digiproductz.com/voizhub-ai-re

Niva Dailynivadaily
2024-09-27

โญ•๏ธเด“เดชเตเดชเดฃเตโ€ เดŽเดเดฏเตเดŸเต† เด…เดกเตเดตเดพเดจเตโ€เดธเตเดกเต เดตเต‹เดฏเดฟเดธเต เดฎเต‹เดกเต: เดšเดพเดฑเตเดฑเต เดœเดฟเดชเดฟเดŸเดฟเด•เตเด•เต เดชเตเดคเดฟเดฏ เดฎเตเด–เด‚
Read full story: nivadaily.com/openai-advanced-
Join our Whatsapp group
chat.whatsapp.com/CktzgxHMaoo8

2024-09-19

๐Ÿ“ˆ I passi avanti sono enormi. Secondo me, non siamo ancora al livello di #ChatGPT nella stessa modalitร . 

___ 

โœ‰๏ธ ๐—ฆ๐—ฒ ๐˜ƒ๐˜‚๐—ผ๐—ถ ๐—ฟ๐—ถ๐—บ๐—ฎ๐—ป๐—ฒ๐—ฟ๐—ฒ ๐—ฎ๐—ด๐—ด๐—ถ๐—ผ๐—ฟ๐—ป๐—ฎ๐˜๐—ผ/๐—ฎ ๐˜€๐˜‚ ๐—พ๐˜‚๐—ฒ๐˜€๐˜๐—ฒ ๐˜๐—ฒ๐—บ๐—ฎ๐˜๐—ถ๐—ฐ๐—ต๐—ฒ, ๐—ถ๐˜€๐—ฐ๐—ฟ๐—ถ๐˜ƒ๐—ถ๐˜๐—ถ ๐—ฎ๐—น๐—น๐—ฎ ๐—บ๐—ถ๐—ฎ ๐—ป๐—ฒ๐˜„๐˜€๐—น๐—ฒ๐˜๐˜๐—ฒ๐—ฟ: bit.ly/newsletter-alessiopomar 

#AI #GenAI #GenerativeAI  #IntelligenzaArtificiale #VoiceTechnology

2024-08-21

๐Ÿ”— Il post di Google: blog.google/technology/health/

๐Ÿ”— L'intervista: alessiopomaro.it/voicewise-voi 

___ 

โœ‰๏ธ ๐—ฆ๐—ฒ ๐˜ƒ๐˜‚๐—ผ๐—ถ ๐—ฟ๐—ถ๐—บ๐—ฎ๐—ป๐—ฒ๐—ฟ๐—ฒ ๐—ฎ๐—ด๐—ด๐—ถ๐—ผ๐—ฟ๐—ป๐—ฎ๐˜๐—ผ/๐—ฎ ๐˜€๐˜‚ ๐—พ๐˜‚๐—ฒ๐˜€๐˜๐—ฒ ๐˜๐—ฒ๐—บ๐—ฎ๐˜๐—ถ๐—ฐ๐—ต๐—ฒ, ๐—ถ๐˜€๐—ฐ๐—ฟ๐—ถ๐˜ƒ๐—ถ๐˜๐—ถ ๐—ฎ๐—น๐—น๐—ฎ ๐—บ๐—ถ๐—ฎ ๐—ป๐—ฒ๐˜„๐˜€๐—น๐—ฒ๐˜๐˜๐—ฒ๐—ฟ: bit.ly/newsletter-alessiopomar 

#AI #GenAI #GenerativeAI  #IntelligenzaArtificiale #VoiceTechnology

2024-08-21

๐Ÿง  Health Acoustic Representations (#HeAR) รจ un modello di #AI di #Google in grado di rilevare malattie attraverso i suoni prodotti dal corpo umano, come la tosse. 

๐Ÿ’ก In India, questa tecnologia viene usata per diagnosticare la tubercolosi rendendo l'assistenza sanitaria piรน accessibile e conveniente.

๐Ÿ‘‰ Tre anni fa, parlavo di questi sistemi con il professor Giovanni Saggio, con risultati giร  sbalorditivi.

#AI #GenAI #GenerativeAI  #IntelligenzaArtificiale #VoiceTechnology

Alessio Pomaro e Giovanni Saggio
2024-08-16

โญ Sembra che gli assistenti che avremmo voluto ai tempi di Alexa e Google Assistant stiano arrivando. 

๐Ÿ”— blog.google/products/gemini/ma

___ 

โœ‰๏ธ ๐—ฆ๐—ฒ ๐˜ƒ๐˜‚๐—ผ๐—ถ ๐—ฟ๐—ถ๐—บ๐—ฎ๐—ป๐—ฒ๐—ฟ๐—ฒ ๐—ฎ๐—ด๐—ด๐—ถ๐—ผ๐—ฟ๐—ป๐—ฎ๐˜๐—ผ/๐—ฎ ๐˜€๐˜‚ ๐—พ๐˜‚๐—ฒ๐˜€๐˜๐—ฒ ๐˜๐—ฒ๐—บ๐—ฎ๐˜๐—ถ๐—ฐ๐—ต๐—ฒ, ๐—ถ๐˜€๐—ฐ๐—ฟ๐—ถ๐˜ƒ๐—ถ๐˜๐—ถ ๐—ฎ๐—น๐—น๐—ฎ ๐—บ๐—ถ๐—ฎ ๐—ป๐—ฒ๐˜„๐˜€๐—น๐—ฒ๐˜๐˜๐—ฒ๐—ฟ: bit.ly/newsletter-alessiopomar 

#AI #GenAI #GenerativeAI  #IntelligenzaArtificiale #LLM #voicetechnology

2024-08-16

๐Ÿง  Sulla scia della modalitร  conversazionale di #OpenAI, anche #Google rilascia #Gemini Live.
๐Ÿ’ก Anche in questo caso, si tratterร  di una conversazione senza turni prestabiliti: sarร  possibile interrompere l'assistente in ogni momento, semplicemente parlando. 
๐Ÿ‘‰ Avrร  10 nuove voci, potrร  interagire con la fotocamera dello smartphone e con le applicazioni Google.
๐Ÿ‘‰ Per ora sarร  solo in lingua inglese e su Android. 

#AI #GenAI #GenerativeAI  #IntelligenzaArtificiale #LLM #voicetechnology

American TeamAmericanTeamNY
2024-07-04

Voice Technology: The Future of Business
Unlock the future of business with voice technology! Integrate voice recognition into your applications to boost accessibility and enhance the user experience. Speak your way to success!

Client Info

Server: https://mastodon.social
Version: 2025.04
Repository: https://github.com/cyevgeniy/lmst