Inworld speech synthesis and provider-managed realtime voice agents.
5 integrated models · Official documentation ↗
Fastest and cheapest model in Inworld's TTS-2 family, launched August 9, 2026 with a quoted 20 ms P90 time to first audio and TTS-2's language coverage and instant voice cloning, but no natural-language steering.
Inworld's flagship text-to-speech, launched May 5, 2026, directed with bracketed natural-language steering for emotion, pacing and non-verbal sounds, plus a deliveryMode setting. Inworld quotes 100 ms P90 time to first audio and 200+ languages and locales.
Quality-focused model of Inworld's TTS-1.5 generation, launched January 21, 2026 with P90 first-audio latency under 250 ms in 15 languages and temperature control. Inworld has since deprecated it in favor of Realtime TTS-2.
Latency-first sibling of TTS-1.5 Max, released January 21, 2026 with P90 first-audio latency under 130 ms across the same 15 languages. Now deprecated; Inworld points latency-sensitive users to TTS-2 Flash.
Inworld's Realtime API, an OpenAI Realtime-compatible speech-to-speech service, set up here with Inworld STT-1 for transcription, GPT-4o for replies and Inworld TTS-2 for voice, with turn detection, interruptions and tool calling over one WebSocket session.
