AUDIO ANALYSIS API

Turn audio into structured JSON

The audio analysis API for developers. POST a file or share a recording link. Define the fields you need, get transcript, sentiment, and more back as JSON in seconds.

No credit card required. 50 free credits to start.
POST /v1/audio
{ "transcript": "...", "sentiment": "frustrated", "speaker_count": 2, "language": "en" }
200 OK · 3.1s

HOW IT WORKS

Audio in, JSON out. Three steps.

01

Define your schema

List the fields you want back, like transcript, sentiment, speaker count, or topics. You choose them, the API fills them in.

02

Send the audio

POST a file directly, or generate a recording link. Users record or upload from any browser, no app needed.

03

Get your JSON

A webhook fires the moment analysis finishes, with the transcript and every field you defined.

ONE SCHEMA ENGINE

What you can pull out of audio

Define the fields you need. The API returns exactly those, structured as JSON, on every recording.

UNIFIED SCHEMA

Define your fields once. Extract them from every recording.

{ sentiment: enum, speaker_count: number, action_items: array }
TXT
Transcript

Full text, timestamps, speaker turns.

SPK
Speakers

Number, turn-taking, diarization labels.

SENT
Sentiment

Positive, negative, frustrated, satisfied.

LANG
Language

Detection across 50+ languages.

TOP
Topics

What was discussed, in your own categories.

ACT
Action items

Promises, requests, follow-ups.

EVT
Audio events

Silence, music, background noise, interruptions.

+
Custom fields

Define a field, get it back.

USE CASES

What teams build with the audio analysis API

Call centers / support

Every call analyzed the moment it ends. Extract sentiment, reason for call, resolution status.

{ sentiment: "frustrated", escalation_flag: true }
Sales teams

Discovery calls turned into CRM updates without rep effort. Extract deal stage, objections, next steps.

{ deal_stage: "negotiation", objections: ["price"] }
QA / compliance

Sample 100 percent of recordings instead of 2 percent. Extract script adherence, prohibited words.

{ script_adherence: true, prohibited_words: [] }
Healthcare

Patient intake calls and symptom voicemails. Extract chief complaint, duration, urgency.

{ chief_complaint: "back pain", urgency: "medium" }
AI agents with ears

Give your voice agent structured context from every call it handles.

{ intent: "cancel_subscription", confidence: 0.94 }
Meetings & interviews

Recorded internally, summarized instantly. Extract attendees, decisions, action items.

{ action_items: 3, owners: ["Jamie"] }

PRICING

Start free. Scale when you need to.

Pay as you go
50 credits free
then $1 per 10 credits
  • 1 credit per minute of audio
  • Files auto-delete after 1 hour
  • Up to 3 assistants for different extraction tasks
  • Custom fields on every request
  • Recording links, up to 5 minutes each
Start free
Pro
$149/mo
2,000 credits included
  • Everything in Pay as you go
  • Shared workspace for up to 3 teammates
  • Unlimited assistants
  • Fine-tune extraction with your own data
  • Custom branding on recording links
  • Unlimited audio length
Start free
Enterprise
Custom
for teams with scale or compliance needs
  • On-premise deployment
  • Custom-trained extraction models
  • Volume discounts
  • Priority support
Contact sales

FAQ

Questions, answered

How is this different from a transcription API?

Transcription gives you the words. We give you structured data. Define a schema, sentiment, action items, topics, anything, and the API returns the transcript plus those fields in the exact JSON shape your app expects.

What audio formats do you support?

MP3, WAV, M4A, AAC, OGG, and FLAC. Files up to 500 MB per request on Pay as you go, unlimited on Pro and Enterprise.

What languages can you handle?

50+ languages, including English, Spanish, French, German, Mandarin, Japanese, and Arabic. Auto-detect, or pass a language hint for higher accuracy.

Can it handle multiple speakers?

Yes. The API distinguishes speakers automatically, labels them, and attaches turn-taking metadata. Define speakers in your schema to get a count or per-speaker fields.

How long does extraction take?

Most extractions finish in under 10 seconds. A 1-minute recording typically returns in 2 to 4 seconds, and the webhook fires the moment it is ready.

How accurate is the transcription?

Word accuracy is typically 92 to 98 percent on clean audio. Every extraction includes a confidence score per field, so you can auto-accept high-confidence results.

Start analyzing audio today

50 free credits. No credit card required.

Start free