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

# Modulate developer docs

> Build with Modulate's voice AI platform. Start with Velma for complete conversation intelligence, or use individual models for transcription, deepfake detection, music & speech detection, emotion detection, PII/PHI redaction and more.

Every model is audio-native — analyzing acoustic signals, not just transcribed words, for more accurate results. Together, these models let you understand the true meaning of every conversation — and act on it in real time.

## Velma

<Card title="Velma: Conversation Understanding" href="/velma/overview">
  Detect behaviors, classify conversations, identify participant roles, and extract topics with sentiment. Velma is the flagship model for developers building complete voice intelligence solutions — available as a single API call or a real-time stream.
</Card>

## Individual models

<CardGroup cols={3}>
  <Card title="Transcription" icon="microphone" href="/get-started/stt">
    Multilingual transcription with speaker diarization, emotion, accent, and PII/PHI tagging — batch or real-time streaming.
  </Card>

  <Card title="Deepfake Detection" icon="shield-halved" href="/get-started/deepfake">
    Per-frame deepfake detection. Classify recorded files or stream live audio for real-time anti-spoofing.
  </Card>

  <Card title="PII/PHI Redaction" icon="eye-slash" href="/get-started/pii">
    Remove sensitive spans from transcripts and silence the matching audio ranges — batch and streaming.
  </Card>

  <Card title="Music & Speech Detection" icon="music" href="/get-started/music-detection">
    Frame-level music and speech probability scoring. Classify a file or stream audio for real-time content analysis.
  </Card>

  <Card title="Language Detection" icon="language" href="/get-started/language-detection">
    Identify the spoken language of an audio file — confidence-scored results across 100 languages in a single synchronous call.
  </Card>
</CardGroup>

Not sure which API fits your use case? See [Which API should I use?](/guides/which-api)

## New here?

<Card title="Quick start" icon="rocket" href="/quickstart">
  Make your first API call in under five minutes — no SDK required.
</Card>

## What you can build

<CardGroup cols={3}>
  <Card title="Meeting transcription" icon="users">
    Multilingual transcripts with speaker labels, timestamps, and optional emotion or accent signals.
  </Card>

  <Card title="Live captions" icon="bolt">
    Stream audio over WebSocket and receive utterances as they're spoken.
  </Card>

  <Card title="Anti-spoofing" icon="shield-check">
    Real-time deepfake detection during voice authentication flows.
  </Card>

  <Card title="Compliance archives" icon="file-shield">
    Shareable recordings with PII/PHI silenced from both transcript and audio.
  </Card>

  <Card title="Content moderation" icon="sliders">
    Classify audio as music, speech, or neither — frame by frame, at scale.
  </Card>

  <Card title="Deepfake screening" icon="magnifying-glass">
    Batch-process uploaded audio to flag AI-generated voice content.
  </Card>
</CardGroup>