Shipped some small quality of life improvements to kontext today. You can now: – change the safety_tolerance (though image inputs are still limited to 2)
– pick an output format (jpg or png) Also, we have two multi-image models now.
MULTIMODAL AI
-
Kontext Updates: Safety Controls and Multi-Image Model Support
By
–
-
Flux Kontext Multi-Image Support Now Available in Pro and Max
By
–
Our experimental flux kontext multi-image support now comes in two flavors, one for pro and one for max: Pro: https://
replicate.com/flux-kontext-a
pps/multi-image-kontext-pro
… Max (original): https://
replicate.com/flux-kontext-a
pps/multi-image-kontext-max
… -
OpenAudio S1 introduces emotional nuance to AI voice synthesis
By
–
Most AI voice tools sound human.
— God of Prompt (@godofprompt) 3 juin 2025
But OpenAudio S1 feels human.
AI voices with emotions, nuance, and soul – just type (empathetic), (angry), (whispering) and it acts it out.
This changes everything. https://t.co/i5cPxoHLkQMost AI voice tools sound human. But OpenAudio S1 feels human. AI voices with emotions, nuance, and soul – just type (empathetic), (angry), (whispering) and it acts it out. This changes everything.
-
Fish Audio AI Voice Tool Now Available for Free
By
–
Ready to Try It? Fish Audio is now live and it’s free to try. If you create content, build products, or just want your own AI voice twin…
This tool belongs in your stack. -
Instant Audio Transcription Using AI Speech-to-Text
By
–
3/ Instant Transcription, No Fuss
— God of Prompt (@godofprompt) 3 juin 2025
Got audio? Fish turns it into perfectly formatted text using Speech to Text.
Great for:
• Lecture notes
• Podcast transcripts
• Captions for social video
And it's lightning fast. pic.twitter.com/byjZblzCaN3/ Instant Transcription, No Fuss Got audio? Fish turns it into perfectly formatted text using Speech to Text.
Great for: • Lecture notes
• Podcast transcripts
• Captions for social video And it's lightning fast. -
Voice Cloning Capabilities of Fish Audio
By
–
2/ Clone Any Voice Yours or Theirs
— God of Prompt (@godofprompt) 3 juin 2025
Fish Audio’s Voice Cloning is next-level.
It captures:
• Accents
• Emotions
• Speech patterns
• Vocal quirks
Perfect for YouTubers, actors, podcasters or anyone building a voice-first brand. pic.twitter.com/BbZjYxNk3X2/ Clone Any Voice Yours or Theirs Fish Audio’s Voice Cloning is next-level. It captures: • Accents
• Emotions
• Speech patterns
• Vocal quirks Perfect for YouTubers, actors, podcasters or anyone building a voice-first brand. -
Fish Audio Launches Voice Cloning and Text-to-Speech Studio
By
–
Meet Fish Audio: The World's Most Capable Voice Cloning and Text-to-Speech Studio Fish Audio offers voice cloning, custom libraries, and studio-quality speech. It delivers speech so real, you’ll think it was human-recorded. https://
fish.audio -
Fish Audio introduces high-accuracy AI voice cloning
By
–
BREAKING: The most realistic AI voice ever just dropped Fish Audio clones anyone with jaw-dropping accuracy You’ve never heard AI sound like this Here's how it works:
-
OpenAI announces two new audio models
By
–
BREAKING : OpenAI is preparing to release 2 new models with native audio support:
– gpt-4o-audio-preview-2025-06-03
– gpt-4o-realtime-preview-2025-06-03 h/t @legit_api -
Cost Tracking for Multi-Modal Inputs and Token Caching
By
–
💹 Track costs across multi-modal inputs and token-caching
— LangChain (@LangChain) 3 juin 2025
Cost tracking is essential for agentic applications because resource usage is determined dynamically by the agent itself. This is becoming trickier now that model providers charge different per-token prices by token… pic.twitter.com/B1pYbsReZpTrack costs across multi-modal inputs and token-caching Cost tracking is essential for agentic applications because resource usage is determined dynamically by the agent itself. This is becoming trickier now that model providers charge different per-token prices by token