Inworld Realtime TTS 2 is Inworld's text to speech model. A low-latency TTS model from Inworld AI featuring natural language steering to control tone and emotion directly within the prompt.
Specifications
Canonical IDinworld-realtime-tts-2
TypeText to Speech
StatusActive
CreatorInworld
Input ModalitiesText
Output ModalitiesAudio

Capabilities

Input1/5
Text
Image·
Audio·
Video·
PDF·
Output1/5
Text·
Image·
Audio
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Inworld Realtime TTS 2Current
Step TTS 2Available
StyleTTS 2Available
TTS HD 2.5Available
Inworld Realtime TTS 1.5 MaxAvailable
Inworld Realtime TTS 1.5 MiniAvailable
Inworld TTS 1 MaxAvailable
Inworld TTS 1.5 MaxAvailable
Inworld TTS 1.5 MiniAvailable
TTS 1Available
TTS 1 HDAvailable

Model IDs

inworld-ai/realtime-tts-2
inworld-realtime-tts-2