Add corrections, implementation notes, pricing changes, or usage caveats for other readers.
Apr 2, 2026
Input modalities
Output modalities
Capabilities
Context window
256,000 tokens
Recent tweets and retweets from Deep Infra
Introducing Realtime TTS-2, a new generation of voice model built for realtime conversation.
It is the first voice model that hears the conversation, takes natural-language voice direction, holds one voice identity across over 100 languages, and speaks like a person who is…
New on DeepInfra: Realtime TTS 2.0 from @inworld_ai
• Prompt emotion + tone in plain English
• Cross-lingual voices
• Built for realtime apps
$35 / 1M characters
Try it here: deepinfra.com/inworld-ai/rea…
DeepInfra has raised its $107M in Series B funding 🚀
AI is moving from training to production-scale deployment, and inference is becoming the system constraint.
DeepInfra was built for this shift — scaling high-throughput inference for open-source and agent-driven…
Discuss this model
Add corrections, implementation notes, pricing changes, or usage caveats for other readers.