
Inworld AI
Inworld AI is an artificial intelligence company focused on building generative voice and character technology for real-time, interactive applications. Its work centers on speech synthesis and conversational AI systems designed to feel natural in dialogue-heavy contexts like games, agents, and media production, where latency and expressiveness matter as much as raw quality.
On Venice, Inworld AI is represented by a single text-to-speech model: Inworld TTS-1.5 Max, released in 2026. It anchors the catalog as a dedicated speech synthesis option rather than a general-purpose text or image model, giving builders access to high-fidelity voice generation alongside Venice's broader lineup of language and multimodal systems.
The lab's positioning leans toward applied, production-grade voice AI rather than open-weight research releases. TTS-1.5 Max reflects that orientation — a flagship speech model tuned for expressive, interactive use cases where conversational pacing and vocal character are the primary differentiators.
🔊TEXT TO SPEECH(1)
Data from Venice API (live pricing + capabilities) and enrichment worker (HuggingFace + Wikipedia + arXiv, refreshed every 12h).