田中義弘 | taziku CEO / AI × Creative (@taziku_co)

GitHub에 공개된 Voicebox 프로젝트를 공유하는 트윗이다. 로컬 음성 생성 AI 도구 Voicebox의 오픈소스 저장소 링크를 안내하며, 관련 정보를 더 확인할 수 있게 한다.

https://x.com/taziku_co/status/2045430868085486017

#opensource #github #voicegeneration #aitool #tts

田中義弘 | taziku CEO / AI × Creative (@taziku_co) on X

Voicebox https://t.co/O4HPbcvwBT via:@ErickSky

X (formerly Twitter)

田中義弘 | taziku CEO / AI × Creative (@taziku_co)

몇 초 분량의 오디오만으로 음성 복제를 지원하는 로컬 음성 생성 AI Voicebox를 소개한다. 23개 언어, 5개 TTS 시스템, DAW 스타일 타임라인을 제공하며, API 없이도 완전 로컬 환경에서 사용할 수 있는 점이 특징인 고품질 음성 합성 도구다.

https://x.com/taziku_co/status/2045430866223243420

#voicegeneration #tts #voiceloning #localai #speechsynthesis

田中義弘 | taziku CEO / AI × Creative (@taziku_co) on X

ローカルで高品質な音声生成AI Voiceboxは、 数秒の音声→声クローン 23言語 5系統TTS DAW風タイムライン 100%ローカル。 音声生成をAPI以外で探す場合 検討の候補に入る。 詳細は🧵

X (formerly Twitter)

Qwen3-TTS Family Is Now Open Sourced: Voice Design, Clone, and Generation

https://qwen.ai/blog?id=qwen3tts-0115

#HackerNews #Qwen3TTS #OpenSource #VoiceDesign #VoiceClone #VoiceGeneration

Qwen

Qwen Chat offers comprehensive functionality spanning chatbot, image and video understanding, image generation, document processing, web search integration, tool utilization, and artifacts.

www.both.org?p=11437

#Linux #AI #VoiceGeneration #Both.org

#AI #VoiceGeneration #DeepFakes

via #TheVerge

"#OpenAI’s voice cloning AI model only needs a 15-second sample to work

 / 

Called Voice Generation, the model has been in development since late 2022 and powers the Read Aloud feature in #ChatGPT."

"# The AI-generated voice can read out text prompts on command in the same language as the speaker or in a number of other languages.👈"
"OpenAI told the publication the model will only be available to about 10 developers."

https://www.theverge.com/2024/3/29/24115701/openai-voice-generation-ai-model

OpenAI’s voice cloning AI model only needs a 15-second sample to work

OpenAI has revealed its Voice Generation model, which can generate new audio using someone’s voice based on just a short clip.

The Verge
This startup gives your speech a new 'human-realistic' AI voice — for free

Spanish startup Voicemod has launched 20 "human-realistic" AI voices that enables users to change in real-time how they sound online.

TNW | Deep-Tech

So, let's start posting.

Here's an infinite discussione generated by AI between Werner Herzog and Slavoj Žižek.

Aside form the hilarity and creepiness, it's quite interesting as it points out issues with deepfakes and generated content in general.

https://infiniteconversation.com/

#AI #VoiceGeneration #Deepfake