Audio Requirements

File formats, size limits, and audio-quality issue codes for recordings.

Supported formats

Format	Notes
`wav`	Lossless quality; larger file sizes
`flac`	Lossless compression; smaller than WAV with no quality loss
`mp3`	Accepted; often smaller than WAV; helps you stay under the 32 MB upload limit
`m4a`	Accepted; common from mobile devices; often smaller than WAV

Format is detected from the file. Anything else returns UNSUPPORTED_FORMAT (400) — Errors.

File size

Limit	Value
Maximum per file	32 MB

For longer recordings, use MP3, M4A, or FLAC to stay under 32 MB.

Duration

Duration	Outcome
Less than 15 seconds	Returns `400 Bad Request`; submit a recording of at least 15 seconds
15–19 seconds	Processed; check `audio_quality` for guidance on use
20–120 seconds	Recommended range for best results
2–20 minutes	Accepted; longer recordings have longer processing times (up to several minutes)
Greater than 20 minutes (1200 seconds)	Returns `400 Bad Request`; trim to 20 minutes or fewer before submitting

Recordings on the shorter end of the 15–19 second range are more likely to produce insufficient_speech issues.

Sample rate

Parameter	Value
Minimum	8000 Hz
Recommended	16000 Hz
Maximum	No hard upper limit; higher rates are downsampled internally

Record and submit at 16000 Hz where possible for best results across all models.

Mono recordings are recommended. Stereo recordings are accepted — the API automatically downmixes stereo input to mono before analysis. For best results, mixing to mono before submitting is still preferred.

Submitting audio

Audio is submitted as multipart/form-data with either an audio file or an audio_upload_ref (the mint response’s upload_ref from POST /v2/audio/uploads). For complete working examples, see the Model API, the Sign API, and Audio Uploads.

Speaker diarization

diarize=true splits speakers and analyzes each. Default false. Use for interviews or group sessions. Flat +50 tokens — Billing and Cost.

When to use diarization

Single speaker — diarize=false (default).
Multiple speakers — diarize=true. Each speaker is analyzed separately.

diarize=true on a single-speaker file still works (one speaker detected).

How to enable

Pass diarize=true as a form field on POST /v2/models/{model_name}/analyze or POST /v2/signs/{sign_name}/analyze.

curl -X POST https://api.amplifierhealth.com/v2/models/pulse/analyze \
  -H "X-Account-ID: your-account-id" \
  -H "X-API-Key: your-api-key" \
  -F "diarize=true" \
  -F "audio=@recording.wav;type=audio/wav"

const fs = require("fs");

const form = new FormData();
form.append("diarize", "true");
form.append("audio", new Blob([fs.readFileSync("recording.wav")], { type: "audio/wav" }), "recording.wav");

const response = await fetch("https://api.amplifierhealth.com/v2/models/pulse/analyze", {
  method: "POST",
  headers: {
    "X-Account-ID": process.env.AMPLIFIER_ACCOUNT_ID,
    "X-API-Key": process.env.AMPLIFIER_API_KEY,
  },
  body: form,
});

const data = await response.json();

# Requires httpx: pip install httpx
import os
import httpx

with open("recording.wav", "rb") as f:
    audio_bytes = f.read()

response = httpx.post(
  "https://api.amplifierhealth.com/v2/models/pulse/analyze",
  headers={
      "X-Account-ID": os.environ["AMPLIFIER_ACCOUNT_ID"],
      "X-API-Key": os.environ["AMPLIFIER_API_KEY"],
  },
  files={"audio": ("recording.wav", audio_bytes, "audio/wav")},
  data={
      "diarize": "true"
  },
)

data = response.json()

Processing time

Diarization adds a speaker-separation step. Long recordings can take several minutes. Submit still returns a job immediately — Jobs, Polling, and Webhooks.

Recording environment guidelines

Environment:

Record in a quiet space with minimal background noise. Open offices, public spaces, and rooms with significant echo are worth avoiding.
Eliminate sources of intermittent noise (fans, air conditioning, notifications) where possible.

Microphone:

Use a close-proximity microphone. Headset microphones, lavaliers, and phone handsets held close to the mouth produce consistently better results than speakerphone or far-field microphones.
Keep levels clear of clipping. If the speaker’s voice is loud, lower the input gain until audio levels peak around -6 dBFS.

Speaker:

Capture a single speaker per recording.
The speaker should be the subject being assessed, not a clinician or interviewer.

Tip Before deploying in a new environment — a clinic room, a mobile app, an enterprise desktop — test recording levels with a sample recording and check audio_quality.issues in the response. Resolve any issues before going live.

Code	Effect on results	Recommended action
`poor_voice_quality`	Recording may be below optimal for analysis	Re-record in a quieter environment with a better microphone
`insufficient_speech`	Limited speech detected; more continuous speech may improve results	Re-record with more active continuous speech; eliminate long pauses
`high_background_noise`	Background noise may affect analysis quality	Re-record in a quieter space or with a closer microphone
`invalid_speaker`	No clear single-speaker human speech detected	Verify the recording contains the intended speaker’s voice

When issues contains invalid_speaker, request a new recording before routing. Routing: The audio_quality object. Fields: Response Schema — audio_quality.