home.social

#voicesynthesis — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #voicesynthesis, aggregated by home.social.

  1. Some improvements to the concatenation, prosody is still missing.

    Here is a well known phrase by SCP 079.

    The audio contains the same phrase first performed by Dr. Sbaitso TTS and the by Godot reimplementation.

    #TTS #DrSbaitso #VoiceSynthesis #TextToSpeech #079 #SCP079 #SCP #Godot

  2. Some improvements to the concatenation, prosody is still missing.

    Here is a well known phrase by SCP 079.

    The audio contains the same phrase first performed by Dr. Sbaitso TTS and the by Godot reimplementation.

    #TTS #DrSbaitso #VoiceSynthesis #TextToSpeech #079 #SCP079 #SCP #Godot

  3. Some improvements to the concatenation, prosody is still missing.

    Here is a well known phrase by SCP 079.

    The audio contains the same phrase first performed by Dr. Sbaitso TTS and the by Godot reimplementation.

    #TTS #DrSbaitso #VoiceSynthesis #TextToSpeech #079 #SCP079 #SCP #Godot

  4. Some improvements to the concatenation, prosody is still missing.

    Here is a well known phrase by SCP 079.

    The audio contains the same phrase first performed by Dr. Sbaitso TTS and the by Godot reimplementation.

    #TTS #DrSbaitso #VoiceSynthesis #TextToSpeech #079 #SCP079 #SCP #Godot

  5. Some improvements to the concatenation, prosody is still missing.

    Here is a well known phrase by SCP 079.

    The audio contains the same phrase first performed by Dr. Sbaitso TTS and the by Godot reimplementation.

    #TTS #DrSbaitso #VoiceSynthesis #TextToSpeech #079 #SCP079 #SCP #Godot

  6. Dr. Sbaitso compared to my reimplementation in Godot (Sbaitso first) :computer_explorer: :pc_color:

    Implemented: basic waveform concatenation
    Missing: Interpolation, pitch control, prosody, text to phonemes

    Im very happy with the progress, will be great to be able to run the voice without needing emulation.

    #TTS #DrSbaitso #VoiceSynthesis #TextToSpeech #079 #SCP079

  7. Dr. Sbaitso compared to my reimplementation in Godot (Sbaitso first) :computer_explorer: :pc_color:

    Implemented: basic waveform concatenation
    Missing: Interpolation, pitch control, prosody, text to phonemes

    Im very happy with the progress, will be great to be able to run the voice without needing emulation.

    #TTS #DrSbaitso #VoiceSynthesis #TextToSpeech #079 #SCP079

  8. Dr. Sbaitso compared to my reimplementation in Godot (Sbaitso first) :computer_explorer: :pc_color:

    Implemented: basic waveform concatenation
    Missing: Interpolation, pitch control, prosody, text to phonemes

    Im very happy with the progress, will be great to be able to run the voice without needing emulation.

    #TTS #DrSbaitso #VoiceSynthesis #TextToSpeech #079 #SCP079

  9. Dr. Sbaitso compared to my reimplementation in Godot (Sbaitso first) :computer_explorer: :pc_color:

    Implemented: basic waveform concatenation
    Missing: Interpolation, pitch control, prosody, text to phonemes

    Im very happy with the progress, will be great to be able to run the voice without needing emulation.

    #TTS #DrSbaitso #VoiceSynthesis #TextToSpeech #079 #SCP079

  10. What I've learned so far while reverse engineering Dr Sbaitso's voice:
    - Reverse engineering is hard

    Also, the voice was made by very clever people. It's optimized to sound as good as possible, while consuming very few resources.

    Progress after 5 days: 10%

    #TTS #DrSbaitso #VoiceSynthesis #TextToSpeech

  11. Ever wondered how AI voices are becoming so human-like? We've moved beyond simple "voice packs" (pre-recorded clips) to true AI "voice clones" that generate new speech from text.

    The magic is in the details: AI models learn a voice's unique pitch and cadence. The secret sauce? "Emotional tuning," which adds happiness, sadness, or empathy to the performance. It's a game-changer for accessibility and content creation. #AIVoice #VoiceSynthesis #Tech

  12. OK, this is probably a rather long shot, but does anyone know of a voice synthesis model that is open-weights or ideally even open-source, and capable of producing intonation (specifically, something like rap lyrics)? #text2speech #voicesynthesis #ai

  13. ChatGPT Advanced Voice Mode impresses testers with sound effects, catching its breath - Enlarge / A stock photo of a robot whispering to a man. (credit: Andrey... - arstechnica.com/?p=2040213 #largelanguagemodels #advancedvoicemode #aivoicegenerators #machinelearning #audiosynthesis #voicesynthesis #textsynthesis #chatgpt #chatgtp #biz#openai #ai

  14. School athletic director arrested for framing principal using AI voice synthesis - Enlarge (credit: Getty Images)

    On Thursday, Baltimore County P... - arstechnica.com/?p=2019931 #machinelearning #audiosynthesis #voicesynthesis #baltimore #deepfakes #aifakes #biz#policy #openai #police #ai

  15. OpenAI holds back wide release of voice-cloning tech due to misuse concerns - Enlarge (credit: Getty Images)

    Voice synthesis has come a long... - arstechnica.com/?p=2008632 #machinelearning #voicesynthesis #voiceengine #aiprivacy #aiethics #aisafety #chatgpt #chatgtp #biz#openai #api #ai

  16. Restoring a Person’s Voice Using a Brain-Computer Interface - Being able to vocalize is one of the most essential elements of the human experien... - hackaday.com/2023/08/28/restor #brain-computerinterface #voicesynthesis #science #phoneme #bci

  17. Thanks to AI, “Elvis” likes big butts and he cannot lie—here’s how it’s possible - Enlarge (credit: Getty Images / Benj Edwards)

    Recently, a numb... - arstechnica.com/?p=1950200 #machinelearning #audiosynthesis #musicsynthesis #thereiruinedit #voicesynthesis #dustinballard #sirmix-a-lot #babygotback #so-vits-svc #johnnycash #culture #biz#elvis #music #tech #ai