> ## Documentation Index
> Fetch the complete documentation index at: https://intervyo.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Interviews

> What an AI-led interview is, how the conversation works, and what gets captured.

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 10–45 minutes depending on the template, and ships a scored
transcript within 2 minutes of ending.

## What makes it an interview, not a chatbot

<CardGroup cols={2}>
  <Card title="Adaptive follow-up" icon="git-branch">
    Probes vague answers, asks for real examples, and adjusts depth based on
    what the participant just said. No fixed question list.
  </Card>

  <Card title="Voice-first, sub-second" icon="mic">
    Real voice latency (`<800ms`) means the AI feels like a person on a phone
    call, not a chatbot streaming tokens.
  </Card>

  <Card title="Calibrated scoring" icon="sliders">
    Every dimension you defined on the template gets graded against your
    rubric — same bar every session, every region.
  </Card>

  <Card title="Authenticity-aware" icon="shield-check">
    Tab-switch, paste, voice-spoofing signals captured continuously and
    surfaced for human judgment.
  </Card>
</CardGroup>

## Channels

| Channel                  | When to use                                                                              | Latency  |
| ------------------------ | ---------------------------------------------------------------------------------------- | -------- |
| **Web (browser)**        | Default. Candidate clicks a join link, AI joins immediately. Camera optional.            | `<800ms` |
| **Outbound phone (SIP)** | High-volume call-center hiring, or when participants can't install/permission a browser. | `<1s`    |
| **Embedded widget**      | Inside your own product or job page — see [Embed guide](/en/guides/embed-widget).        | `<800ms` |

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

## 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.

<Tip>
  Scores are directly comparable across languages — the AI uses the same
  rubric dimensions and weighting regardless of which language the interview
  ran in.
</Tip>

## Lifecycle in one diagram

```text theme={null}
  ┌──────────────┐   created    ┌──────────────┐   joined     ┌──────────────┐
  │   scheduled  │ ───────────► │  in_progress │ ───────────► │   completed  │
  └──────────────┘              └──────────────┘              └──────────────┘
         │                              │
         │ candidate doesn't show       │ candidate hangs up early /
         ▼                              ▼ tech failure
  ┌──────────────┐              ┌──────────────┐
  │   cancelled  │              │    failed    │
  └──────────────┘              └──────────────┘
```

See [Sessions](/en/concepts/sessions) for what's emitted at each transition
and what fields are populated.

## What gets captured

Every interview produces a structured **session record** with these fields:

<ResponseField name="transcript" type="string[]">
  Time-stamped speaker turns. AI and participant labeled separately.
</ResponseField>

<ResponseField name="recording_url" type="string">
  Presigned URL to the audio recording. Short-lived (1 hour by default);
  request a fresh URL each time you need access.
</ResponseField>

<ResponseField name="score" type="number">
  Overall rubric score 0–10. Weighted average of per-dimension scores.
</ResponseField>

<ResponseField name="evaluation_breakdown" type="object[]">
  Per-dimension scores with reasoning paragraphs and transcript citations.
  See [Rubrics](/en/concepts/rubrics) for the shape.
</ResponseField>

<ResponseField name="authenticity_signals" type="object">
  Tab-switch count, paste events, voice-spoofing flags, screen-share
  detections. Surfaced verbatim — no auto-pass-fail interpretation.
</ResponseField>

<ResponseField name="ai_feedback" type="string">
  Two-paragraph plain-English summary: what the participant did well, what
  the next-round interviewer should probe. Generated against your rubric.
</ResponseField>

## Re-running an interview

Interviews are immutable once `completed` or `failed`. To run another one
for the same participant — say after a technical glitch — create a new
session. The participant's prior sessions stay attached for history.

<Note>
  Multi-Round Roles auto-create a fresh session for each Round. You
  don't need to manually re-create sessions when a candidate progresses
  through Rounds — see [Roles](/en/concepts/roles).
</Note>