Kotoba Technologies · Voice
Kotoba Sts v1 Realtime Voice
Speak in one language, hear it in another. Streaming speech-to-speech translation with the translated text alongside the audio.
Evidence and sources
Released 24 Jun 2026
Sources: Fal.ai data, llminfo researchPrimary data from Fal.ai
from llminfo research: release date
Input & output
from the model's typeText
Audio
Text
Audio
Also known as: kotoba-technologies/kotoba-sts/v1/realtime_voice
Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works