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 2————Current
Realtime TTS-2————Available
Realtime TTS-2 Research Preview————Available
Soniox TTS 2 RT————Available
Step TTS 2————Available
StyleTTS 2————Available
TTS HD 2.5————Available
VoxCPM2————Available
TTS 1—$15.00—Deprecating
TTS 1 HD—$30.00—Deprecating
Inworld Realtime TTS 1.5 Max————Available

Model IDs

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