Audio Configuration - Medera

Overview

Speech to Text

Facial Physiological Engine

Vocal Acoustic Engine

Neurobehavioral Construct Computer

Supported formats

Format	Real-time	Batch
PCM 16-bit (16 kHz)	✓	✓
PCM 16-bit (44.1 / 48 kHz)	✓ (downsampled)	✓
Opus	✓	✓
WAV (PCM)	—	✓
MP3 (CBR)	—	✓
M4A / AAC	—	✓
OGG (Opus)	✓	✓
FLAC	—	✓

Recommended

16 kHz 16-bit PCM mono
Opus at 32 kbps for bandwidth-constrained edges

Frame size

For real-time, send 20 ms frames (320 samples at 16 kHz). Anything smaller wastes WS overhead; anything larger inflates latency.

/transcripts endpoint Audio Events