NEW Sentient Emotional API

The emotional AI layer for every application.

One API to understand how people feel — in calls, messages and AI conversations. Analyse emotion, build long-term emotional profiles and catch cloned voices, then plug it into your apps, CRM, BI or AI agents.

Built for everyone from solo developers and SMEs to the world's largest platforms.

ISO 27001 certified99 languagesOpenAPI 3.1MCP-readyGDPR-ready
71
Engagement
✓ Human voice
Authenticity · low risk
F / A / C vectors
F
0.41
A
0.33
C
0.12
500+
Emotions, behaviours & events
Voice + language
99
Languages
Voice and text
4
Core capabilities
Analyse · Profile · Authenticate · Report
Minutes
To your first result
Free sandbox · no card
The platform

Everything emotion, in one API.

Use one capability or all five. Every response is structured JSON — ready for your database, your dashboards or your AI agent.

How it works

From conversation to insight in three calls.

1

Send

POST /analyses/audio or /analyses/text. Pre-signed URL, direct upload or JSON — authenticated with your API key.

2

Receive

A signed analysis.completed webhook, or poll. ERI, F/A/C vectors, emotions, behaviours and AEHS as structured JSON.

3

Act

GET /profiles/customers/{ref} for the emotional fingerprint. GET /insights/aggregates for your dashboards.

Why Sentient

Deeper than sentiment. Built to integrate.

  • Hears and reads. Voice tone and language analysed together — catches what words alone miss.
  • Explainable risk. The Emotional Risk Index breaks feelings into Frustration, Anxiety and Calm.
  • Remembers people. Longitudinal profiling judges each person against their own norm — fewer false alarms, earlier warnings.
  • Spots fakes. Emotional-congruence analysis catches synthetic voices that sound right but don't react right.
  • Goes anywhere. REST, webhooks, client tokens, no-code and MCP. No lock-in, any industry.
Person profile · CUST-2231 Proactive contact
Baseline ERI
18.2
Current ERI
27.4
personal norm
Trend↘ deteriorating
Deviation from normz = 2.4
Repeat-contact chain3 · active
Profile confidence86%
ERI has risen 9.2 points above this person's own norm across their last three conversations. Webhook fired to CRM: proactive contact recommended.
Solutions

One API. Endless places to use it.

If people talk, type or speak to your AI, Sentient helps you understand them — in any industry.

Revenue

Outbound & inside sales

Coach every rep on every call; spot hesitation and objections.

Revenue

Deal & account health

Emotional warmth on every CRM contact and account.

Experience

Customer experience

Emotion by journey step, product and channel.

Experience

Contact centres & BPOs

QA at 100% coverage and targeted coaching.

AI

Chatbots & voice bots

Adapt tone and hand off at the right moment.

AI

LLM agents & copilots

Emotion and profiles as a tool call or MCP server.

Deepfake analysis

Deepfake analysis

Spot cloned and AI-generated voices across 16 high-risk scenarios. See below ↓

Security

Fraud & scam signals

Pressure and urgency patterns routed to fraud teams.

Product

Product & UX research

Emotion timelines across interviews and tests.

Product

Voice of customer

Reviews, surveys and social, scored and trended.

People

Coaching & wellbeing apps

Feedback on tone; mood check-ins (non-diagnostic).

People

Gaming & communities

Player frustration and toxicity signals.

Use case · Deepfake analysis

Is that voice real? Find out before it costs you.

Voice cloning takes seconds and fools people and voiceprints alike. Sentient scores calls, voice notes and audio clips for synthetic-voice risk — and checks what clones still get wrong: genuine emotional reaction.

ScreenSynthetic-voice risk on every recording
VerifyKerr Test probes for live, high-risk calls
ActRisk webhooks into fraud, IVR & T&S tools
Financial

Account takeover

Cloned voices calling to change details, reset access or move money.

Financial

CEO / CFO payment fraud

“Urgent transfer” calls and voice notes impersonating executives.

Financial

Voice-biometric hardening

An extra authenticity layer on top of voiceprint log-in.

Financial

Crypto & trading withdrawals

Checks before withdrawals, recoveries and limit changes.

Enterprise

Help-desk & MFA resets

Attackers posing as staff to reset passwords or MFA.

Enterprise

Meeting impersonation

Screen the audio of Teams, Zoom and Meet calls for cloned voices.

Enterprise

Remote hiring & onboarding

Synthetic voices used by fake candidates or new starters.

Consumer

Family-emergency scams

“Mum, I need help” voice notes in messaging apps.

Consumer

Romance & marketplace scams

AI voices used to build false trust on dating and selling platforms.

Consumer

Telecom & SIM-swap fraud

Voice checks before number ports, SIM swaps and plan changes.

Consumer

Insurance claims

Claims phoned in with a borrowed or cloned voice.

Media

Newsroom verification

Check viral audio clips before they’re published or shared.

Media

Election & disinformation monitoring

Flag synthetic audio of public figures at scale.

Media

Platform content moderation

Detect synthetic audio uploads on social and UGC platforms.

Public & legal

Public-service helplines

Protect tax, benefits and healthcare lines from impersonation.

Public & legal

Evidence & investigations

Risk indicators on audio submitted in disputes and investigations.

Scores are risk indicators that trigger further checks — not proof on their own.How deepfake analysis works →

Developers & start-ups

Ship an emotion feature this afternoon.

  • Free sandbox, no card
  • Pay-as-you-go
  • SDKs, client tokens, MCP

SMEs & growing teams

Insight without a data team.

  • No-code connectors
  • CRM & helpdesk recipes
  • Simple monthly plans

Enterprises & platforms

The emotion engine inside your product.

  • Volume & wholesale pricing
  • White-label and OEM
  • Regional processing, SLAs
Voice Authenticity

Sounds human. Doesn't feel human.

Voice clones can fool people and voiceprints. Sentient checks what fakes still get wrong — how a real person emotionally reacts — alongside the acoustic traces of synthetic speech. For high-risk moments, the Kerr Test uses short, natural probes that real people respond to and clones don't.

  • Synthetic-voice risk on every call
  • Emotional-congruence analysis
  • Kerr Test active verification
  • Real-time risk webhooks
Explore Voice Authenticity →
Authenticity check · CALL-90412High risk
Synthetic-voice risk
0.87
Emotional congruence
0.91
Acoustic artefacts
0.79
Emotional flatness
0.74
Response dynamics
0.52
Recommended: run_kerr_test before processing the payment request.
Integrations

Fits the stack you already run.

CRM, sales tools, helpdesks, telephony, meetings, warehouses, BI, no-code and AI frameworks — if it can make an HTTPS call, it can use Sentient.

Telephony & CCaaSRecording exports
CRM & sales toolsProfile fields
Chat & emailSync text API
Data warehousesParquet exports
BI toolsAggregates
AI & no-codeMCP · Zapier · Make
Developers & AI builders

Give your app — and your AI — emotional intelligence.

Copy-paste REST, client tokens for web and mobile, and drop-in tool definitions so any LLM agent can read emotion and remember how people feel.

  • Free sandbox, OpenAPI 3.1 spec
  • Client tokens for browser and mobile
  • Tool definitions + MCP server for LLM agents
  • Signed webhooks, idempotent retries
Start in the sandbox →
curl https://sandbox.api.sentientmachines.tech/v1/analyses/text \
  -H "Authorization: Bearer $SENTIENT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "mode": "sync",
    "format": "chat",
    "messages": [
      {"speaker": "customer", "text": "Third time I have called about this."},
      {"speaker": "agent", "text": "I am sorry. I will fix it now."}
    ],
    "reference": {"customer_ref": "CUST-2231"}
  }'
import os, requests

r = requests.post(
    "https://sandbox.api.sentientmachines.tech/v1/analyses/text",
    headers={"Authorization": f"Bearer {os.environ['SENTIENT_API_KEY']}"},
    json={"mode": "sync", "format": "email",
          "text": "I'm really worried about this bill."},
)
eri = r.json()["summary"]["eri"]
print(eri["score"], eri["band"])
const res = await fetch(
  "https://sandbox.api.sentientmachines.tech/v1/profiles/customers/CUST-2231",
  { headers: { Authorization: `Bearer ${process.env.SENTIENT_API_KEY}` } }
);
const profile = await res.json();
if (profile.deviation.flagged) {
  queueProactiveContact(profile.customer_ref, profile.recommended_action);
}
// Any MCP-capable assistant or agent framework
{
  "mcpServers": {
    "sentient": {
      "command": "npx",
      "args": ["-y", "@sentient/mcp-server"],
      "env": { "SENTIENT_API_KEY": "snt_live_…" }
    }
  }
}
// Tools: sentient_analyse_text · sentient_get_emotional_profile
//        sentient_check_voice_authenticity · sentient_team_insights
Trust

Safe by default.

Emotion data deserves the highest standard of care — for your customers and your colleagues.

Data minimisation

Pseudonymised references only. Audio isn't retained unless you choose.

Redaction on

Card numbers, account numbers, phone numbers and emails masked by default.

Ring-fenced wellbeing signals

A restricted permission for supporting people — never pricing, targeting or matching.

Jurisdiction-aware

EU mode removes voice-based emotion inference on employees. UK and EU regions.

Emotion signals are for understanding and helping people — never for manipulation, lie detection or diagnosis. See our Acceptable Use Policy.

Make every application emotionally intelligent.

Start free in the sandbox. Scale on pay-as-you-go — or talk to us about enterprise and platform partnerships.

Get API keyTalk to sales
Design reference · draft