VOICE AUTHENTICATOR

Analyze the caller.

Upload a stereo call or open My Audios to detect synthetic speech on Caller CH0.

Vionis Flash

VIONIS/Voice Authenticator

Vionis Flash

Analyze Caller CH0 with Agent CH1 as conversation context.

SplitFocus

CALL RECORDINGSTEREO PCM

CallerCH 0Subject channel

Choose a recording to view this channel

AgentCH 1Context channel

Choose a recording to view this channel

00:0000:0000:0000:0000:00

00:00 / 00:00

Upload a recording or open My Audios

CALLER CH0 ASSESSMENTFLASH

Awaiting analysis

Choose a call recording, then run analysis.

—Flash processing

Model classification does not verify caller identity. Confidence is the score for the returned verdict.

SOURCE FORMATStereo PCM WAV

Caller CH0 is classified. Agent CH1 provides turn-taking context.

DETECTION MODELVionis Flash

Acoustic features and conversational timing, with a degraded-line fallback.

PROCESSINGLive endpoint

Run analysis submits the original WAV to Flash. Results stay in this session.

Analysis sends audio to Vionis Flash. Model predictions can be wrong; semantic verification is not included.API docs

A human classification does not confirm the caller’s identity.