1. Connect your service
Checking speech service…
2. Choose your audio and output
Start with six-second captions. Select the spoken language explicitly for the most reliable translation.
3. Capture and save
Ready
Stop and let pending audio finish before downloading. Audio is not saved; closing the tab can lose pending audio and unsaved text.
4. Capture settings
Save or import local preferences. Tokens, microphone identifiers, room names and sharing are excluded. Connect first, then load settings for that service.
Advanced options
Relay sharing, self-hosting, remote setup and diagnostics.
Send captions to captions.coop
Optional: caption text travels through the room’s private relay. Audio stays on the inference host. The editor reviews captions before publishing them to the audience room.
For a direct overlay, use its room instead. Anyone with that room link can see the shared text; direct captions skip human review.
Use a private relay
A private relay needs its own room token, separate from the room admin link. The editor needs the source viewing token and output publishing token. Links carry the relay address, never tokens. Turn sharing off before changing these settings.
Sharing off
Direct monitor: Open source overlay (bypasses review; carries the viewing token in the link fragment).
Using your own self-hosted instance
This page connects to the instance that serves it. To use a different self-hosted instance, open its own capture page. Credentials are never sent to another origin.
Connection and capture diagnostics
- Model
- —
- Device
- —
- Precision
- —
- Processing now
- —
- Waiting
- —
- Version
- —
- Buffered audio
- —
- Pending audio
- —
- Failed audio
- —
- Recent requests
- —
- Last response
- —
- Server processing
- —
- Network + upload
- —
- Requested language
- —
- Detected language
- —
- Audience output
- —
Response duration includes network, queue and inference time; it is not speech-to-caption delay. The last 100 requests are retained in memory. Downloads exclude tokens, service addresses, room names, audio and captions.