Soniox TTS 2 RT is Soniox's text to speech model. A real-time TTS model from Soniox optimized for low-latency streaming speech synthesis in live voice applications.
Specifications
Canonical IDsoniox-tts-2-rt
TypeText to Speech
StatusActive
CreatorSoniox
Input ModalitiesText
Output ModalitiesAudio
Benchmarks
Elo Rating
#107

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
Soniox TTS 2 RTCurrent
Inworld Realtime TTS 2Available
Realtime TTS-2 Research PreviewAvailable
Step TTS 2Available
StyleTTS 2Available
TTS HD 2.5Available
TTS 1$15.00Deprecating
TTS 1 HD$30.00Deprecating
Inworld Realtime TTS 1.5 MaxAvailable
Inworld Realtime TTS 1.5 MiniAvailable
Inworld TTS 1 MaxAvailable

Model IDs

soniox-tts-2-rt
soniox-tts-rt-v2