Modulate’s Velma-2 platform delivers production-grade voice AI: multilingual transcription, synthetic-voice detection, and PII/PHI redaction — over both REST and WebSocket.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.
Quick start
Get your first API call working in minutes with working Python examples for every endpoint.
Guides
How-to articles covering audio formats, authentication, enrichment features, and choosing the right API.
API reference
Full request and response schemas for every endpoint — STT batch, streaming, deepfake detection, and redaction.
FAQ
Authentication, pricing, audio requirements, rate limits, privacy, and data handling.
Support
Get help, report a bug, or request a feature — we respond within one business day.
What you can build
Transcription
Multilingual speech-to-text with speaker diarization, emotion, accent, and PII/PHI tagging.
Real-time captions
Stream audio over WebSocket and receive utterances as they’re spoken.
Deepfake detection
Per-frame synthetic voice detection — batch and streaming.
PII/PHI redaction
Replace sensitive spans in transcripts and silence the matching audio ranges.
Voice authentication
Real-time anti-spoofing checks during a voice login flow.
Compliance archives
Shareable recordings with sensitive content removed — text and audio.