Skip to main content
An interview is a real-time voice conversation between a calibrated AI interviewer and one participant. It runs in the browser or over a phone call, lasts 10โ€“45 minutes depending on the template, and ships a scored transcript within 2 minutes of ending.

โ€‹
What makes it an interview, not a chatbot

Adaptive follow-up

Probes vague answers, asks for real examples, and adjusts depth based on what the participant just said. No fixed question list.

Voice-first, sub-second

Real voice latency (<800ms) means the AI feels like a person on a phone call, not a chatbot streaming tokens.

Calibrated scoring

Every dimension you defined on the template gets graded against your rubric โ€” same bar every session, every region.

Authenticity-aware

Tab-switch, paste, voice-spoofing signals captured continuously and surfaced for human judgment.

โ€‹
Channels

The session record is identical across channels โ€” same scorecard format, same transcript shape, same webhook payload. Pick the channel that matches where your participants are.

โ€‹
Languages

intervyo.ai conducts interviews in English, Japanese, Hindi, Spanish, and several more, with rubric-aligned scoring per language. Set the language on the Role (language field) or per-session by passing it to the create-session endpoint.
Scores are directly comparable across languages โ€” the AI uses the same rubric dimensions and weighting regardless of which language the interview ran in.

โ€‹
Lifecycle in one diagram

See Sessions for whatโ€™s emitted at each transition and what fields are populated.

โ€‹
What gets captured

Every interview produces a structured session record with these fields:
โ€‹
string[]
Time-stamped speaker turns. AI and participant labeled separately.
โ€‹
string
Presigned URL to the audio recording. Short-lived (1 hour by default); request a fresh URL each time you need access.
โ€‹
number
Overall rubric score 0โ€“10. Weighted average of per-dimension scores.
โ€‹
object[]
Per-dimension scores with reasoning paragraphs and transcript citations. See Rubrics for the shape.
โ€‹
object
Tab-switch count, paste events, voice-spoofing flags, screen-share detections. Surfaced verbatim โ€” no auto-pass-fail interpretation.
โ€‹
string
Two-paragraph plain-English summary: what the participant did well, what the next-round interviewer should probe. Generated against your rubric.

โ€‹
Re-running an interview

Interviews are immutable once completed or failed. To run another one for the same participant โ€” say after a technical glitch โ€” create a new session. The participantโ€™s prior sessions stay attached for history.
Multi-Round Roles auto-create a fresh session for each Round. You donโ€™t need to manually re-create sessions when a candidate progresses through Rounds โ€” see Roles.
Last modified on June 30, 2026