Nova Sonic Bridge

The call

Bridge endpoint

Token (deployed only)

Like an inbound call: the agent speaks first, then you reply. Talking over it triggers barge-in.

The deployed endpoint is public and needs the token. Local needs no token. If a connection just hangs, check the endpoint and token above.

Choose .wav file

No file chosen.

Live mic streams continuously, like a real phone line.

Nothing yet.

frames sent

frames recv

KB sent

KB recv

—

sample rate

Messages appear here as they go over the socket. Base64 is truncated for readability — the real length is shown after each one.

PCM16	The raw audio itself — 16 000 sample values per second, 2 bytes each, signed, −32768…+32767. Not a codec or container; a speaker plays it directly.
base64	Only present because JSON is text and raw bytes would break the string. Costs ~33% in size and is perfectly reversible.
one frame	32 ms of audio = 512 samples = 1024 bytes raw → 1368 base64 chars → ~1397 bytes of JSON (1.36×).
passthrough	The bridge copies this base64 string straight into Nova Sonic's `audioInput.content` field and copies its reply straight back out. No transcoding.
turn taking	There is no "end of turn" message. Nova Sonic's own voice-activity detection decides when you stopped talking, so silence must keep flowing — which is why the file mode appends 1.5 s of silence after your clip.
resampling	This page converts whatever you upload to 16 kHz mono before sending. In production that job belongs at the LiveKit edge, not in the bridge.