Get the analysis
curl --request GET \
--url https://api.eesi.ai/v1/speech/transcriptions/{session_id}/intelligence \
--header 'Authorization: Bearer <token>'import requests
url = "https://api.eesi.ai/v1/speech/transcriptions/{session_id}/intelligence"
headers = {"Authorization": "Bearer <token>"}
response = requests.get(url, headers=headers)
print(response.text)const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};
fetch('https://api.eesi.ai/v1/speech/transcriptions/{session_id}/intelligence', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://api.eesi.ai/v1/speech/transcriptions/{session_id}/intelligence",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "GET",
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"net/http"
"io"
)
func main() {
url := "https://api.eesi.ai/v1/speech/transcriptions/{session_id}/intelligence"
req, _ := http.NewRequest("GET", url, nil)
req.Header.Add("Authorization", "Bearer <token>")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.get("https://api.eesi.ai/v1/speech/transcriptions/{session_id}/intelligence")
.header("Authorization", "Bearer <token>")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.eesi.ai/v1/speech/transcriptions/{session_id}/intelligence")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Get.new(url)
request["Authorization"] = 'Bearer <token>'
response = http.request(request)
puts response.read_body{
"id": "097e5805-ca84-46a4-addb-69712072b960",
"intelligence": {
"status": "complete",
"stage": "complete",
"progress": 1,
"run_id": "ff18b767e178",
"version": "p1.2",
"duration": 1060.009,
"segments": [
{
"id": 44,
"speaker": "S01",
"start": 277.22,
"end": 282.08,
"speech_start": 277.34,
"speech_end": 281.02,
"prosody": {
"energy_db": -11.5,
"energy_range_db": 10.8,
"voiced_ratio": 0.77,
"pitch_hz": 219.9,
"pitch_range_st": 7.5,
"pitch_variability_st": 3.45,
"pitch_perturbation": 0.0102,
"amplitude_perturbation": 0.07,
"hnr_db": 10.4,
"pauses": [
{
"start": 279.52,
"end": 279.86,
"duration": 0.34,
"after_word": "determined",
"filled": false,
"sentence_end": false
}
],
"articulation_rate": 3.98,
"pace_wpm": 123,
"hesitations": 0,
"longest_pause": 0.34,
"pace_vs_speaker": -0.064,
"pitch_vs_speaker_st": 0.98,
"energy_vs_speaker_db": 0.2,
"pitch_range_vs_speaker_st": -0.9
},
"perception": {
"emotion": "neutral",
"intensity": 0.5,
"valence": 0,
"arousal": 0.2,
"confidence": 0.9,
"engagement": 0.65,
"take_quality": 0.9,
"delivery": [
"rushed",
"emphatic"
],
"reactions": [],
"emphasis": [
"determined",
"cannot",
"deterred"
],
"audio_issues": [
"off_mic"
],
"note": "Strong, definitive finish.",
"start": 277.22,
"end": 282.08
},
"delivery": {
"score": 0.87,
"label": "great",
"flags": [
{
"type": "emphatic",
"source": "heard"
}
]
},
"emphasis": [
{
"word_index": 5,
"word": "determined",
"start": 278.92,
"end": 279.52,
"strength": 1,
"source": "heard"
},
{
"word_index": 7,
"word": "cannot",
"start": 280.06,
"end": 280.36,
"strength": 1,
"source": "heard"
},
{
"word_index": 9,
"word": "deterred.",
"start": 280.58,
"end": 281.02,
"strength": 1,
"source": "heard"
}
],
"quality": {
"snr_db": 16.6,
"noise_db": -29.5,
"clipping_ratio": 0,
"low_frequency_share_db": -23.5,
"wind_index": 0,
"plosives": 0,
"mic": "medium",
"score": 1,
"issues": [
{
"type": "off_mic",
"severity": 0.4,
"evidence": "heard by the listener",
"source": "heard"
}
]
},
"ambience": {
"layers": [],
"sound": {},
"competes": false,
"source": "estimate"
}
}
],
"events": [
{
"type": "applause",
"start": 519.6,
"end": 528.52,
"speaker": "S01",
"during_speech": true,
"confidence": 0.988,
"sources": [
"located"
]
},
{
"type": "pace_shift",
"at": 25.77,
"speaker": "S01",
"change": -0.34,
"direction": "slower",
"source": "measured",
"start": 25.77,
"end": 25.77
}
],
"speakers": {
"S01": {
"talk_seconds": 1049.9,
"turns": 182,
"hesitations": 233,
"trajectory": [
{
"t": 6.58,
"start": 2.25,
"end": 10.91,
"segment_id": 0,
"emotion": "neutral",
"valence": 0,
"arousal": 0.2,
"confidence": 0.65,
"engagement": 0.65,
"energy_db": -13.4,
"score": 0.59
}
],
"confidence": 0.745,
"engagement": 0.668,
"valence": 0.009,
"arousal": 0.237,
"emotions": {
"neutral": 0.944,
"calm": 0.056
},
"delivery_labels": {
"hesitant": 8,
"good": 148,
"great": 12,
"weak": 2
},
"articulation_rate": 4.26,
"pitch_hz": 207.8,
"pitch_range_st": 8.4,
"fillers_per_minute": 0,
"reactions": {},
"summary": "The speaker is generally confident and authoritative, particularly during high-energy segments (15:52-15:58). They occasionally struggle with specific words or technical phrasing, leading to noticeable hesitations (7:33-7:41) and strained, rushed delivery (0:02-0:10)."
}
},
"moments": [
{
"type": "select",
"start": 323.32,
"end": 325.05,
"speaker": "S01",
"score": 0.89,
"reason": "Whole sentence; more pitch movement than usual (+3.1 st); Applause follows",
"segment_ids": [
53
],
"text": "We mean to be a part of it.",
"sentence_complete": true,
"id": "select-32332"
},
{
"type": "unusable",
"start": 221.98,
"end": 224.29,
"speaker": "S01",
"score": 0.61,
"reason": "Audio: off mic",
"segment_ids": [
36
],
"id": "unusable-22198"
},
{
"type": "trim",
"start": 5.01,
"end": 5.93,
"speaker": "S01",
"score": 1.22,
"reason": "Tighten a 1.2s pause",
"segment_ids": [
0
],
"id": "trim-501"
}
],
"recovered": [],
"music": [],
"ambience_profile": [
{
"start": 0,
"end": 10,
"label": "a train station or airport",
"score": 0.1992
}
],
"baselines": {
"S01": {
"pitch_hz": 207.8,
"pitch_range_st": 8.4,
"articulation_rate": 4.25,
"energy_db": -11.7,
"pitch_perturbation": 0.009,
"energy_range_db": 11.05
}
},
"coverage": {
"segments": 182,
"listened": 182
},
"conditions": [
{
"type": "hum",
"evidence": "60 Hz mains hum through the recording",
"source": "measured"
},
{
"type": "off_mic",
"evidence": "The voice is off mic throughout, as from a PA or a room microphone",
"source": "measured"
}
],
"summary": {
"overview": "A formal address featuring a single speaker delivering a structured, high-energy speech. The recording is characterized by authoritative list-making and emphatic transitions, punctuated by periodic applause.",
"speakers": [
{
"speaker": "S01",
"summary": "The speaker is generally confident and authoritative, particularly during high-energy segments (15:52-15:58). They occasionally struggle with specific words or technical phrasing, leading to noticeable hesitations (7:33-7:41) and strained, rushed delivery (0:02-0:10)."
}
],
"watch_outs": [
"Off-mic/Unusable audio: 3:41-3:44, 6:48-6:50, 7:10-7:11, 9:02-9:04, 16:22-16:23, 16:38-16:39",
"Mumbled/Whispered: 14:52-14:54",
"Long hesitations/Stumbles: 0:02-0:10, 7:17-7:27, 7:33-7:41, 14:39-14:45"
]
},
"timings": {
"total": 132.8
},
"completed_at": "2026-10-07T17:29:45.701084+00:00"
},
"speaker_map": {
"S01": {
"speaker_id": "c5b9be33-e08b-4cca-81ad-65387bf33622",
"number": 3,
"name": "John F. Kennedy",
"similarity": 0.709,
"matched": true
}
},
"project": {
"id": "e4af92a4-3bf6-467b-95a2-7b04fb610d1c",
"key": "presidential-speeches",
"name": "Presidential speeches",
"speakers": [
{
"id": "3650e649-f065-4da2-832d-ce9dfa62f744",
"number": 1,
"name": "Radio announcer",
"label": "P1",
"clip_count": 1,
"evidence_seconds": 3.5
},
{
"id": "cfb15e2e-5dd2-42b8-bccc-f4f78cae747c",
"number": 2,
"name": "Franklin D. Roosevelt",
"label": "P2",
"clip_count": 4,
"evidence_seconds": 121.3
},
{
"id": "c5b9be33-e08b-4cca-81ad-65387bf33622",
"number": 3,
"name": "John F. Kennedy",
"label": "P3",
"clip_count": 2,
"evidence_seconds": 72
}
]
}
}{
"detail": [
{
"loc": [
"<string>"
],
"msg": "<string>",
"type": "<string>",
"input": "<unknown>",
"ctx": {}
}
]
}Audio intelligence
Get the analysis
The analysis of a recording: how each line was delivered, the audience’s reactions, each speaker’s profile and arc, the moments worth a look, and a written summary.
status is queued, running, complete, failed, unavailable (the
recording has no audio or no speech) or none (never analyzed). While it runs,
stage and progress say how far it is, and the document fills in as it goes:
measurements first, then what each line sounds like, then the summary. Poll every
few seconds until complete.
Every signal says what backs it in source: measured (read from the audio
signal), heard (from listening to the line), or both.
GET
/
v1
/
speech
/
transcriptions
/
{session_id}
/
intelligence
Get the analysis
curl --request GET \
--url https://api.eesi.ai/v1/speech/transcriptions/{session_id}/intelligence \
--header 'Authorization: Bearer <token>'import requests
url = "https://api.eesi.ai/v1/speech/transcriptions/{session_id}/intelligence"
headers = {"Authorization": "Bearer <token>"}
response = requests.get(url, headers=headers)
print(response.text)const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};
fetch('https://api.eesi.ai/v1/speech/transcriptions/{session_id}/intelligence', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://api.eesi.ai/v1/speech/transcriptions/{session_id}/intelligence",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "GET",
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"net/http"
"io"
)
func main() {
url := "https://api.eesi.ai/v1/speech/transcriptions/{session_id}/intelligence"
req, _ := http.NewRequest("GET", url, nil)
req.Header.Add("Authorization", "Bearer <token>")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.get("https://api.eesi.ai/v1/speech/transcriptions/{session_id}/intelligence")
.header("Authorization", "Bearer <token>")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.eesi.ai/v1/speech/transcriptions/{session_id}/intelligence")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Get.new(url)
request["Authorization"] = 'Bearer <token>'
response = http.request(request)
puts response.read_body{
"id": "097e5805-ca84-46a4-addb-69712072b960",
"intelligence": {
"status": "complete",
"stage": "complete",
"progress": 1,
"run_id": "ff18b767e178",
"version": "p1.2",
"duration": 1060.009,
"segments": [
{
"id": 44,
"speaker": "S01",
"start": 277.22,
"end": 282.08,
"speech_start": 277.34,
"speech_end": 281.02,
"prosody": {
"energy_db": -11.5,
"energy_range_db": 10.8,
"voiced_ratio": 0.77,
"pitch_hz": 219.9,
"pitch_range_st": 7.5,
"pitch_variability_st": 3.45,
"pitch_perturbation": 0.0102,
"amplitude_perturbation": 0.07,
"hnr_db": 10.4,
"pauses": [
{
"start": 279.52,
"end": 279.86,
"duration": 0.34,
"after_word": "determined",
"filled": false,
"sentence_end": false
}
],
"articulation_rate": 3.98,
"pace_wpm": 123,
"hesitations": 0,
"longest_pause": 0.34,
"pace_vs_speaker": -0.064,
"pitch_vs_speaker_st": 0.98,
"energy_vs_speaker_db": 0.2,
"pitch_range_vs_speaker_st": -0.9
},
"perception": {
"emotion": "neutral",
"intensity": 0.5,
"valence": 0,
"arousal": 0.2,
"confidence": 0.9,
"engagement": 0.65,
"take_quality": 0.9,
"delivery": [
"rushed",
"emphatic"
],
"reactions": [],
"emphasis": [
"determined",
"cannot",
"deterred"
],
"audio_issues": [
"off_mic"
],
"note": "Strong, definitive finish.",
"start": 277.22,
"end": 282.08
},
"delivery": {
"score": 0.87,
"label": "great",
"flags": [
{
"type": "emphatic",
"source": "heard"
}
]
},
"emphasis": [
{
"word_index": 5,
"word": "determined",
"start": 278.92,
"end": 279.52,
"strength": 1,
"source": "heard"
},
{
"word_index": 7,
"word": "cannot",
"start": 280.06,
"end": 280.36,
"strength": 1,
"source": "heard"
},
{
"word_index": 9,
"word": "deterred.",
"start": 280.58,
"end": 281.02,
"strength": 1,
"source": "heard"
}
],
"quality": {
"snr_db": 16.6,
"noise_db": -29.5,
"clipping_ratio": 0,
"low_frequency_share_db": -23.5,
"wind_index": 0,
"plosives": 0,
"mic": "medium",
"score": 1,
"issues": [
{
"type": "off_mic",
"severity": 0.4,
"evidence": "heard by the listener",
"source": "heard"
}
]
},
"ambience": {
"layers": [],
"sound": {},
"competes": false,
"source": "estimate"
}
}
],
"events": [
{
"type": "applause",
"start": 519.6,
"end": 528.52,
"speaker": "S01",
"during_speech": true,
"confidence": 0.988,
"sources": [
"located"
]
},
{
"type": "pace_shift",
"at": 25.77,
"speaker": "S01",
"change": -0.34,
"direction": "slower",
"source": "measured",
"start": 25.77,
"end": 25.77
}
],
"speakers": {
"S01": {
"talk_seconds": 1049.9,
"turns": 182,
"hesitations": 233,
"trajectory": [
{
"t": 6.58,
"start": 2.25,
"end": 10.91,
"segment_id": 0,
"emotion": "neutral",
"valence": 0,
"arousal": 0.2,
"confidence": 0.65,
"engagement": 0.65,
"energy_db": -13.4,
"score": 0.59
}
],
"confidence": 0.745,
"engagement": 0.668,
"valence": 0.009,
"arousal": 0.237,
"emotions": {
"neutral": 0.944,
"calm": 0.056
},
"delivery_labels": {
"hesitant": 8,
"good": 148,
"great": 12,
"weak": 2
},
"articulation_rate": 4.26,
"pitch_hz": 207.8,
"pitch_range_st": 8.4,
"fillers_per_minute": 0,
"reactions": {},
"summary": "The speaker is generally confident and authoritative, particularly during high-energy segments (15:52-15:58). They occasionally struggle with specific words or technical phrasing, leading to noticeable hesitations (7:33-7:41) and strained, rushed delivery (0:02-0:10)."
}
},
"moments": [
{
"type": "select",
"start": 323.32,
"end": 325.05,
"speaker": "S01",
"score": 0.89,
"reason": "Whole sentence; more pitch movement than usual (+3.1 st); Applause follows",
"segment_ids": [
53
],
"text": "We mean to be a part of it.",
"sentence_complete": true,
"id": "select-32332"
},
{
"type": "unusable",
"start": 221.98,
"end": 224.29,
"speaker": "S01",
"score": 0.61,
"reason": "Audio: off mic",
"segment_ids": [
36
],
"id": "unusable-22198"
},
{
"type": "trim",
"start": 5.01,
"end": 5.93,
"speaker": "S01",
"score": 1.22,
"reason": "Tighten a 1.2s pause",
"segment_ids": [
0
],
"id": "trim-501"
}
],
"recovered": [],
"music": [],
"ambience_profile": [
{
"start": 0,
"end": 10,
"label": "a train station or airport",
"score": 0.1992
}
],
"baselines": {
"S01": {
"pitch_hz": 207.8,
"pitch_range_st": 8.4,
"articulation_rate": 4.25,
"energy_db": -11.7,
"pitch_perturbation": 0.009,
"energy_range_db": 11.05
}
},
"coverage": {
"segments": 182,
"listened": 182
},
"conditions": [
{
"type": "hum",
"evidence": "60 Hz mains hum through the recording",
"source": "measured"
},
{
"type": "off_mic",
"evidence": "The voice is off mic throughout, as from a PA or a room microphone",
"source": "measured"
}
],
"summary": {
"overview": "A formal address featuring a single speaker delivering a structured, high-energy speech. The recording is characterized by authoritative list-making and emphatic transitions, punctuated by periodic applause.",
"speakers": [
{
"speaker": "S01",
"summary": "The speaker is generally confident and authoritative, particularly during high-energy segments (15:52-15:58). They occasionally struggle with specific words or technical phrasing, leading to noticeable hesitations (7:33-7:41) and strained, rushed delivery (0:02-0:10)."
}
],
"watch_outs": [
"Off-mic/Unusable audio: 3:41-3:44, 6:48-6:50, 7:10-7:11, 9:02-9:04, 16:22-16:23, 16:38-16:39",
"Mumbled/Whispered: 14:52-14:54",
"Long hesitations/Stumbles: 0:02-0:10, 7:17-7:27, 7:33-7:41, 14:39-14:45"
]
},
"timings": {
"total": 132.8
},
"completed_at": "2026-10-07T17:29:45.701084+00:00"
},
"speaker_map": {
"S01": {
"speaker_id": "c5b9be33-e08b-4cca-81ad-65387bf33622",
"number": 3,
"name": "John F. Kennedy",
"similarity": 0.709,
"matched": true
}
},
"project": {
"id": "e4af92a4-3bf6-467b-95a2-7b04fb610d1c",
"key": "presidential-speeches",
"name": "Presidential speeches",
"speakers": [
{
"id": "3650e649-f065-4da2-832d-ce9dfa62f744",
"number": 1,
"name": "Radio announcer",
"label": "P1",
"clip_count": 1,
"evidence_seconds": 3.5
},
{
"id": "cfb15e2e-5dd2-42b8-bccc-f4f78cae747c",
"number": 2,
"name": "Franklin D. Roosevelt",
"label": "P2",
"clip_count": 4,
"evidence_seconds": 121.3
},
{
"id": "c5b9be33-e08b-4cca-81ad-65387bf33622",
"number": 3,
"name": "John F. Kennedy",
"label": "P3",
"clip_count": 2,
"evidence_seconds": 72
}
]
}
}{
"detail": [
{
"loc": [
"<string>"
],
"msg": "<string>",
"type": "<string>",
"input": "<unknown>",
"ctx": {}
}
]
}