announcement: https://
inworld.ai/blog/realtime-
tts-2?utm_source=x&utm_medium=social&utm_campaign=tts-2
…
MULTIMODAL AI
-
Inworld AI Launches Realtime TTS-2 Text-to-Speech Model
By
–
-
Inworld AI Launches Realtime TTS-2 Context-Aware Voice Model
By
–
SPEECHLESS.@Inworld_ai, the team behind the #1 TTS model on @ArtificialAnlys, just dropped `Realtime TTS-2` 🤯
— Charly Wargnier (@DataChaz) 5 mai 2026
>It analyzes your tone
>You direct it like an LLM
>It keeps your exact voice across 100+ languages
We just leveled up from text-to-speech to context-to-speech 🔥↓ https://t.co/3g5T1oy5Qe pic.twitter.com/VAvmADyONBSPEECHLESS. @Inworld_ai
, the team behind the #1 TTS model on @ArtificialAnlys
, just dropped `Realtime TTS-2` >It analyzes your tone >You direct it like an LLM
>It keeps your exact voice across 100+ languages We just leveled up from text-to-speech to context-to-speech ↓ -
AI avatar chatbots now use live video for customer service
By
–
Website customer service chatbots can now have an AI avatar talking to you through live video.
— AI Breakfast (@AiBreakfast) 5 mai 2026
In retrospect, it was inevitable. https://t.co/igrqowqXcSWebsite customer service chatbots can now have an AI avatar talking to you through live video. In retrospect, it was inevitable.
-
AI avatar chatbots now offer live video customer service
By
–
Website customer service chatbots can now have an AI avatar talking to you through live video.
— AI Breakfast (@AiBreakfast) 5 mai 2026
In retrospect, it was inevitable. https://t.co/igrqowqXcSWebsite customer service chatbots can now have an AI avatar talking to you through live video. In retrospect, it was inevitable.
-
OpenAI Rolls Out GPT-5.5 Instant as ChatGPT Default Model
By
–
Nice, big update: OpenAI is rolling out GPT-5.5 Instant in ChatGPT as the new default model (very good jumps in benchmark)
— Chubby♨️ (@kimmonismus) 5 mai 2026
The upgrade makes ChatGPT smarter, more factual, more dependable, and better at everyday tasks like image analysis, STEM questions, writing, and… https://t.co/nCVzwAthVX pic.twitter.com/wkCTvfuI4gNice, big update: OpenAI is rolling out GPT-5.5 Instant in ChatGPT as the new default model (very good jumps in benchmark) The upgrade makes ChatGPT smarter, more factual, more dependable, and better at everyday tasks like image analysis, STEM questions, writing, and
-
Persistent Visual Memory for Deep Generation in LVLMs
By
–
Persistent Visual Memory Sustaining Perception for Deep Generation in LVLMs paper: https://
huggingface.co/papers/2605.00
814
… -
MolmoAct2: Action Reasoning Models for Real-World Deployment
By
–
MolmoAct2
— AK (@_akhaliq) 5 mai 2026
Action Reasoning Models for Real-world Deployment
paper: https://t.co/aKO4mzBqBz pic.twitter.com/6IYcKJtzFKMolmoAct2 Action Reasoning Models for Real-world Deployment paper: https://
huggingface.co/papers/2605.02
881
… -
New Book Release: RAG-Driven Generative AI Techniques
By
–
New Release (2nd edition) from @PacktDataML available at https://
amzn.to/4tULP1b RAG-Driven Generative AI — Build MAS-RAG with DualRAG, GraphRAG, multimodal video pipelines, and Oracle Database 23ai 𝗞𝗲𝘆 𝗙𝗲𝗮𝘁𝘂𝗿𝗲𝘀:
Master DualRAG by combining vector search with SQL -
Realtime TTS-2: AI hears how you say it
By
–
Realtime TTS-2 by @inworld_ai most voice ai hears what you say this one hears how you say it <200ms. 100+ languages. one voice
-
Gemini Pro 3.1 Capabilities vs. App Interface: A Curious Discrepancy
By
–
Alex Karp now sounding like @garymarcus.
— Gary Marcus (@GaryMarcus) 5 mai 2026
Sooner or later, everyone figures it out. https://t.co/6OqhRN46bmAlex Karp now sounding like @garymarcus
. Sooner or later, everyone figures it out.