FlashLabs (@flashlabsdotai)
Chroma 1.0을 공개했습니다 — 세계 최초의 오픈소스 종단간 실시간 음성→음성(speech-to-speech) 모델로 개인 맞춤 음성 클로닝을 지원합니다. FlashLabs가 훈련하고 FlashAI에 배포되었으며, 연구급(open research-grade)으로 @OpenAI의 Realtime에 대한 오픈 대안으로 소개됩니다.
https://x.com/flashlabsdotai/status/2013993446047158550
#chroma #speech2speech #voicecloning #opensource
FlashLabs (@flashlabsdotai) on X
Today we’re releasing Chroma 1.0
→ the world first open-source, end-to-end, real-time speech-to-speech model
→ with personalized voice cloning
Trained by FlashLabs.
Deployed on FlashAI👉 https://t.co/5VHCOQFei2
An open research-grade alternative to the @OpenAI Realtime
Version 4.0.0 - BAF 4.0.0
- 75% cost reduction vs #Competition
• #AWS #AmazonBedrock integration
• #FinetuningAI options
• #KnowledgeBase compatibility
• Advanced #RAG implementation
• #CloudComputing solutions
🔜 2025 Roadmap:
- #Speech2Speech model
- #MultiModalAI support
OpenAI & Figure claim nothing on this demo was tricked, sped up etc. Very impressive combination of robotics, interaction with speech and use of AI. Realise that this is just the beginning and first prototype, in a few year it will improve rapidly.
https://www.youtube.com/watch?v=Sq1QZB5baNw#OpenAI #Figure #Robotics #Speech2Speech #AI
Figure Status Update - OpenAI Speech-to-Speech Reasoning
Das Robotik-Startup Figure präsentiert stolz seinen autonom betriebenen Bot "Figure 01", der nahtlos mit der OpenAI Speech-to-Speech-KI funktioniert und komplexe Aufgaben erledigen kann.
#figure01 #openai #roboter #robot #ai #ki #speech2speech
Roboter + KI =
https://youtu.be/Sq1QZB5baNw?si=uQ7THQP3ylRQ81Na
Figure Status Update - OpenAI Speech-to-Speech Reasoning
sayzard
Jordi Cabot
michabbb
Erik Jonker
Subraum Transmissionen [h3rb]