Speak and listen
Have a voice conversation without composing a text prompt for every turn.
MOSS LiveBeta
MOSS Live: Real-Time AI Voice Chat
Speak naturally with MOSS Live. Practice languages, rehearse interviews and enjoy an interruptible voice conversation with live captions.
10 credits / minuteYour credits work across all models.
Start a live conversation
Use the live voice studio for natural interruptions, captions and a free 60-second preview after signing in.
Start a live conversation01 / Inside the model
A conversation that moves with you.
MOSS Live brings speech and visual context into one real-time model. The official API accepts microphone audio and camera or screen frames, then responds with speech and text. Our current browser studio focuses on voice: talk naturally, follow live captions and interrupt a response when you want to take the next turn. Start a conversation from your microphone without installing an app.
Follow the words
Read live captions alongside the conversation in the current browser tab.
Keep the conversation moving
Interrupt playback and take the next turn without waiting for a long answer.
02 / Examples & listening room
Explore the official modelSee it. Hear it. Get a feel for it.
Official examples are credited to OpenMOSS. Studio samples were generated by us with the named API model. These are saved previews, not a result of your current settings. Research capabilities and available studio controls may differ.
Try a real conversation
Open the voice studio for an interactive session. Sign in and allow your microphone to start.
Try the model03 / Use cases
Where it fits.
Language practice
Rehearse everyday conversations and ask follow-up questions aloud.
Think out loud
Explore an idea or work through a problem with spoken feedback.
04 / Questions
A few things worth knowing.
How is MOSS Live different from text to speech?
Live is an interactive session that listens and responds. TTS turns a prepared script into a reusable audio file.
How are calls charged?
Connected call time costs 10 credits per minute, billed in 6-second blocks at one credit per block.
Does this studio use my camera?
No. The current browser studio uses audio only. The official model also supports visual context, but camera and screen sharing are not enabled in this experience.
Made for your next idea
Choose a model, add your input and review the credit cost. Successful results stay in your account history; AI output may be inaccurate.
Text is rounded up to a whole credit. Audio is billed per started minute. Live voice uses one credit per 6 seconds.
Failed tasks are refunded automatically.
Result links can expire. Download files you want to keep.
Model documentation