AssemblyAI

AssemblyAI

curl --request POST \
  --url https://mavi-backend.memories.ai/serve/api/v2/transcriptions/speech-to-text \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "provider": "<string>",
  "asset_id": "<string>",
  "url": "<string>",
  "source_url": "<string>",
  "language_code": "<string>",
  "punctuate": true,
  "format_text": true,
  "speaker_labels": true,
  "speakers_expected": 123,
  "language_detection": true,
  "language_confidence_threshold": 123,
  "speech_model": "<string>",
  "speech_threshold": 123,
  "disfluencies": true,
  "sentiment_analysis": true,
  "entity_detection": true,
  "auto_highlights": true,
  "content_safety": true,
  "iab_categories": true,
  "auto_chapters": true,
  "summarization": true,
  "summary_model": "<string>",
  "summary_type": "<string>",
  "redact_pii": true,
  "redact_pii_policies": [
    "<string>"
  ],
  "redact_pii_sub": "<string>",
  "redact_pii_audio": true,
  "redact_pii_audio_quality": "<string>",
  "filter_profanity": true,
  "word_boost": [
    "<string>"
  ],
  "boost_param": "<string>",
  "custom_spelling": [
    {}
  ],
  "webhook_url": "<string>",
  "multichannel": true,
  "audio_start_from": 123,
  "audio_end_at": 123,
  "custom_topics": true,
  "topics": [
    "<string>"
  ]
}
'

import requests

url = "https://mavi-backend.memories.ai/serve/api/v2/transcriptions/speech-to-text"

payload = {
    "provider": "<string>",
    "asset_id": "<string>",
    "url": "<string>",
    "source_url": "<string>",
    "language_code": "<string>",
    "punctuate": True,
    "format_text": True,
    "speaker_labels": True,
    "speakers_expected": 123,
    "language_detection": True,
    "language_confidence_threshold": 123,
    "speech_model": "<string>",
    "speech_threshold": 123,
    "disfluencies": True,
    "sentiment_analysis": True,
    "entity_detection": True,
    "auto_highlights": True,
    "content_safety": True,
    "iab_categories": True,
    "auto_chapters": True,
    "summarization": True,
    "summary_model": "<string>",
    "summary_type": "<string>",
    "redact_pii": True,
    "redact_pii_policies": ["<string>"],
    "redact_pii_sub": "<string>",
    "redact_pii_audio": True,
    "redact_pii_audio_quality": "<string>",
    "filter_profanity": True,
    "word_boost": ["<string>"],
    "boost_param": "<string>",
    "custom_spelling": [{}],
    "webhook_url": "<string>",
    "multichannel": True,
    "audio_start_from": 123,
    "audio_end_at": 123,
    "custom_topics": True,
    "topics": ["<string>"]
}
headers = {
    "Authorization": "<authorization>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: '<authorization>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    provider: '<string>',
    asset_id: '<string>',
    url: '<string>',
    source_url: '<string>',
    language_code: '<string>',
    punctuate: true,
    format_text: true,
    speaker_labels: true,
    speakers_expected: 123,
    language_detection: true,
    language_confidence_threshold: 123,
    speech_model: '<string>',
    speech_threshold: 123,
    disfluencies: true,
    sentiment_analysis: true,
    entity_detection: true,
    auto_highlights: true,
    content_safety: true,
    iab_categories: true,
    auto_chapters: true,
    summarization: true,
    summary_model: '<string>',
    summary_type: '<string>',
    redact_pii: true,
    redact_pii_policies: ['<string>'],
    redact_pii_sub: '<string>',
    redact_pii_audio: true,
    redact_pii_audio_quality: '<string>',
    filter_profanity: true,
    word_boost: ['<string>'],
    boost_param: '<string>',
    custom_spelling: [{}],
    webhook_url: '<string>',
    multichannel: true,
    audio_start_from: 123,
    audio_end_at: 123,
    custom_topics: true,
    topics: ['<string>']
  })
};

fetch('https://mavi-backend.memories.ai/serve/api/v2/transcriptions/speech-to-text', 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://mavi-backend.memories.ai/serve/api/v2/transcriptions/speech-to-text",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'provider' => '<string>',
    'asset_id' => '<string>',
    'url' => '<string>',
    'source_url' => '<string>',
    'language_code' => '<string>',
    'punctuate' => true,
    'format_text' => true,
    'speaker_labels' => true,
    'speakers_expected' => 123,
    'language_detection' => true,
    'language_confidence_threshold' => 123,
    'speech_model' => '<string>',
    'speech_threshold' => 123,
    'disfluencies' => true,
    'sentiment_analysis' => true,
    'entity_detection' => true,
    'auto_highlights' => true,
    'content_safety' => true,
    'iab_categories' => true,
    'auto_chapters' => true,
    'summarization' => true,
    'summary_model' => '<string>',
    'summary_type' => '<string>',
    'redact_pii' => true,
    'redact_pii_policies' => [
        '<string>'
    ],
    'redact_pii_sub' => '<string>',
    'redact_pii_audio' => true,
    'redact_pii_audio_quality' => '<string>',
    'filter_profanity' => true,
    'word_boost' => [
        '<string>'
    ],
    'boost_param' => '<string>',
    'custom_spelling' => [
        [
                
        ]
    ],
    'webhook_url' => '<string>',
    'multichannel' => true,
    'audio_start_from' => 123,
    'audio_end_at' => 123,
    'custom_topics' => true,
    'topics' => [
        '<string>'
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: <authorization>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://mavi-backend.memories.ai/serve/api/v2/transcriptions/speech-to-text"

	payload := strings.NewReader("{\n  \"provider\": \"<string>\",\n  \"asset_id\": \"<string>\",\n  \"url\": \"<string>\",\n  \"source_url\": \"<string>\",\n  \"language_code\": \"<string>\",\n  \"punctuate\": true,\n  \"format_text\": true,\n  \"speaker_labels\": true,\n  \"speakers_expected\": 123,\n  \"language_detection\": true,\n  \"language_confidence_threshold\": 123,\n  \"speech_model\": \"<string>\",\n  \"speech_threshold\": 123,\n  \"disfluencies\": true,\n  \"sentiment_analysis\": true,\n  \"entity_detection\": true,\n  \"auto_highlights\": true,\n  \"content_safety\": true,\n  \"iab_categories\": true,\n  \"auto_chapters\": true,\n  \"summarization\": true,\n  \"summary_model\": \"<string>\",\n  \"summary_type\": \"<string>\",\n  \"redact_pii\": true,\n  \"redact_pii_policies\": [\n    \"<string>\"\n  ],\n  \"redact_pii_sub\": \"<string>\",\n  \"redact_pii_audio\": true,\n  \"redact_pii_audio_quality\": \"<string>\",\n  \"filter_profanity\": true,\n  \"word_boost\": [\n    \"<string>\"\n  ],\n  \"boost_param\": \"<string>\",\n  \"custom_spelling\": [\n    {}\n  ],\n  \"webhook_url\": \"<string>\",\n  \"multichannel\": true,\n  \"audio_start_from\": 123,\n  \"audio_end_at\": 123,\n  \"custom_topics\": true,\n  \"topics\": [\n    \"<string>\"\n  ]\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "<authorization>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://mavi-backend.memories.ai/serve/api/v2/transcriptions/speech-to-text")
  .header("Authorization", "<authorization>")
  .header("Content-Type", "application/json")
  .body("{\n  \"provider\": \"<string>\",\n  \"asset_id\": \"<string>\",\n  \"url\": \"<string>\",\n  \"source_url\": \"<string>\",\n  \"language_code\": \"<string>\",\n  \"punctuate\": true,\n  \"format_text\": true,\n  \"speaker_labels\": true,\n  \"speakers_expected\": 123,\n  \"language_detection\": true,\n  \"language_confidence_threshold\": 123,\n  \"speech_model\": \"<string>\",\n  \"speech_threshold\": 123,\n  \"disfluencies\": true,\n  \"sentiment_analysis\": true,\n  \"entity_detection\": true,\n  \"auto_highlights\": true,\n  \"content_safety\": true,\n  \"iab_categories\": true,\n  \"auto_chapters\": true,\n  \"summarization\": true,\n  \"summary_model\": \"<string>\",\n  \"summary_type\": \"<string>\",\n  \"redact_pii\": true,\n  \"redact_pii_policies\": [\n    \"<string>\"\n  ],\n  \"redact_pii_sub\": \"<string>\",\n  \"redact_pii_audio\": true,\n  \"redact_pii_audio_quality\": \"<string>\",\n  \"filter_profanity\": true,\n  \"word_boost\": [\n    \"<string>\"\n  ],\n  \"boost_param\": \"<string>\",\n  \"custom_spelling\": [\n    {}\n  ],\n  \"webhook_url\": \"<string>\",\n  \"multichannel\": true,\n  \"audio_start_from\": 123,\n  \"audio_end_at\": 123,\n  \"custom_topics\": true,\n  \"topics\": [\n    \"<string>\"\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://mavi-backend.memories.ai/serve/api/v2/transcriptions/speech-to-text")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = '<authorization>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"provider\": \"<string>\",\n  \"asset_id\": \"<string>\",\n  \"url\": \"<string>\",\n  \"source_url\": \"<string>\",\n  \"language_code\": \"<string>\",\n  \"punctuate\": true,\n  \"format_text\": true,\n  \"speaker_labels\": true,\n  \"speakers_expected\": 123,\n  \"language_detection\": true,\n  \"language_confidence_threshold\": 123,\n  \"speech_model\": \"<string>\",\n  \"speech_threshold\": 123,\n  \"disfluencies\": true,\n  \"sentiment_analysis\": true,\n  \"entity_detection\": true,\n  \"auto_highlights\": true,\n  \"content_safety\": true,\n  \"iab_categories\": true,\n  \"auto_chapters\": true,\n  \"summarization\": true,\n  \"summary_model\": \"<string>\",\n  \"summary_type\": \"<string>\",\n  \"redact_pii\": true,\n  \"redact_pii_policies\": [\n    \"<string>\"\n  ],\n  \"redact_pii_sub\": \"<string>\",\n  \"redact_pii_audio\": true,\n  \"redact_pii_audio_quality\": \"<string>\",\n  \"filter_profanity\": true,\n  \"word_boost\": [\n    \"<string>\"\n  ],\n  \"boost_param\": \"<string>\",\n  \"custom_spelling\": [\n    {}\n  ],\n  \"webhook_url\": \"<string>\",\n  \"multichannel\": true,\n  \"audio_start_from\": 123,\n  \"audio_end_at\": 123,\n  \"custom_topics\": true,\n  \"topics\": [\n    \"<string>\"\n  ]\n}"

response = http.request(request)
puts response.read_body

{
  "code": 200,
  "msg": "success",
  "data": {
    "id": "9a27d0d5-d2db-448c-823c-f098507789be",
    "status": "completed",
    "language_code": "en_us",
    "audio_url": "https://storage.googleapis.com/...",
    "audio_duration": 52,
    "text": "Hello, how are you today? I'm doing well, thank you.",
    "words": [
      {
        "text": "Hello,",
        "start": 0,
        "end": 520,
        "confidence": 0.99,
        "speaker": "A"
      },
      {
        "text": "how",
        "start": 520,
        "end": 780,
        "confidence": 0.98,
        "speaker": "A"
      }
    ],
    "utterances": [
      {
        "confidence": 0.97,
        "start": 0,
        "end": 2980,
        "text": "Hello, how are you today?",
        "speaker": "A"
      },
      {
        "confidence": 0.95,
        "start": 2980,
        "end": 5200,
        "text": "I'm doing well, thank you.",
        "speaker": "B"
      }
    ],
    "confidence": 0.97,
    "punctuate": true,
    "format_text": true,
    "speaker_labels": true,
    "speakers_expected": 2
  },
  "failed": false,
  "success": true
}

POST

serve

api

transcriptions

speech-to-text

AssemblyAI

curl --request POST \
  --url https://mavi-backend.memories.ai/serve/api/v2/transcriptions/speech-to-text \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "provider": "<string>",
  "asset_id": "<string>",
  "url": "<string>",
  "source_url": "<string>",
  "language_code": "<string>",
  "punctuate": true,
  "format_text": true,
  "speaker_labels": true,
  "speakers_expected": 123,
  "language_detection": true,
  "language_confidence_threshold": 123,
  "speech_model": "<string>",
  "speech_threshold": 123,
  "disfluencies": true,
  "sentiment_analysis": true,
  "entity_detection": true,
  "auto_highlights": true,
  "content_safety": true,
  "iab_categories": true,
  "auto_chapters": true,
  "summarization": true,
  "summary_model": "<string>",
  "summary_type": "<string>",
  "redact_pii": true,
  "redact_pii_policies": [
    "<string>"
  ],
  "redact_pii_sub": "<string>",
  "redact_pii_audio": true,
  "redact_pii_audio_quality": "<string>",
  "filter_profanity": true,
  "word_boost": [
    "<string>"
  ],
  "boost_param": "<string>",
  "custom_spelling": [
    {}
  ],
  "webhook_url": "<string>",
  "multichannel": true,
  "audio_start_from": 123,
  "audio_end_at": 123,
  "custom_topics": true,
  "topics": [
    "<string>"
  ]
}
'

import requests

url = "https://mavi-backend.memories.ai/serve/api/v2/transcriptions/speech-to-text"

payload = {
    "provider": "<string>",
    "asset_id": "<string>",
    "url": "<string>",
    "source_url": "<string>",
    "language_code": "<string>",
    "punctuate": True,
    "format_text": True,
    "speaker_labels": True,
    "speakers_expected": 123,
    "language_detection": True,
    "language_confidence_threshold": 123,
    "speech_model": "<string>",
    "speech_threshold": 123,
    "disfluencies": True,
    "sentiment_analysis": True,
    "entity_detection": True,
    "auto_highlights": True,
    "content_safety": True,
    "iab_categories": True,
    "auto_chapters": True,
    "summarization": True,
    "summary_model": "<string>",
    "summary_type": "<string>",
    "redact_pii": True,
    "redact_pii_policies": ["<string>"],
    "redact_pii_sub": "<string>",
    "redact_pii_audio": True,
    "redact_pii_audio_quality": "<string>",
    "filter_profanity": True,
    "word_boost": ["<string>"],
    "boost_param": "<string>",
    "custom_spelling": [{}],
    "webhook_url": "<string>",
    "multichannel": True,
    "audio_start_from": 123,
    "audio_end_at": 123,
    "custom_topics": True,
    "topics": ["<string>"]
}
headers = {
    "Authorization": "<authorization>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: '<authorization>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    provider: '<string>',
    asset_id: '<string>',
    url: '<string>',
    source_url: '<string>',
    language_code: '<string>',
    punctuate: true,
    format_text: true,
    speaker_labels: true,
    speakers_expected: 123,
    language_detection: true,
    language_confidence_threshold: 123,
    speech_model: '<string>',
    speech_threshold: 123,
    disfluencies: true,
    sentiment_analysis: true,
    entity_detection: true,
    auto_highlights: true,
    content_safety: true,
    iab_categories: true,
    auto_chapters: true,
    summarization: true,
    summary_model: '<string>',
    summary_type: '<string>',
    redact_pii: true,
    redact_pii_policies: ['<string>'],
    redact_pii_sub: '<string>',
    redact_pii_audio: true,
    redact_pii_audio_quality: '<string>',
    filter_profanity: true,
    word_boost: ['<string>'],
    boost_param: '<string>',
    custom_spelling: [{}],
    webhook_url: '<string>',
    multichannel: true,
    audio_start_from: 123,
    audio_end_at: 123,
    custom_topics: true,
    topics: ['<string>']
  })
};

fetch('https://mavi-backend.memories.ai/serve/api/v2/transcriptions/speech-to-text', 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://mavi-backend.memories.ai/serve/api/v2/transcriptions/speech-to-text",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'provider' => '<string>',
    'asset_id' => '<string>',
    'url' => '<string>',
    'source_url' => '<string>',
    'language_code' => '<string>',
    'punctuate' => true,
    'format_text' => true,
    'speaker_labels' => true,
    'speakers_expected' => 123,
    'language_detection' => true,
    'language_confidence_threshold' => 123,
    'speech_model' => '<string>',
    'speech_threshold' => 123,
    'disfluencies' => true,
    'sentiment_analysis' => true,
    'entity_detection' => true,
    'auto_highlights' => true,
    'content_safety' => true,
    'iab_categories' => true,
    'auto_chapters' => true,
    'summarization' => true,
    'summary_model' => '<string>',
    'summary_type' => '<string>',
    'redact_pii' => true,
    'redact_pii_policies' => [
        '<string>'
    ],
    'redact_pii_sub' => '<string>',
    'redact_pii_audio' => true,
    'redact_pii_audio_quality' => '<string>',
    'filter_profanity' => true,
    'word_boost' => [
        '<string>'
    ],
    'boost_param' => '<string>',
    'custom_spelling' => [
        [
                
        ]
    ],
    'webhook_url' => '<string>',
    'multichannel' => true,
    'audio_start_from' => 123,
    'audio_end_at' => 123,
    'custom_topics' => true,
    'topics' => [
        '<string>'
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: <authorization>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://mavi-backend.memories.ai/serve/api/v2/transcriptions/speech-to-text"

	payload := strings.NewReader("{\n  \"provider\": \"<string>\",\n  \"asset_id\": \"<string>\",\n  \"url\": \"<string>\",\n  \"source_url\": \"<string>\",\n  \"language_code\": \"<string>\",\n  \"punctuate\": true,\n  \"format_text\": true,\n  \"speaker_labels\": true,\n  \"speakers_expected\": 123,\n  \"language_detection\": true,\n  \"language_confidence_threshold\": 123,\n  \"speech_model\": \"<string>\",\n  \"speech_threshold\": 123,\n  \"disfluencies\": true,\n  \"sentiment_analysis\": true,\n  \"entity_detection\": true,\n  \"auto_highlights\": true,\n  \"content_safety\": true,\n  \"iab_categories\": true,\n  \"auto_chapters\": true,\n  \"summarization\": true,\n  \"summary_model\": \"<string>\",\n  \"summary_type\": \"<string>\",\n  \"redact_pii\": true,\n  \"redact_pii_policies\": [\n    \"<string>\"\n  ],\n  \"redact_pii_sub\": \"<string>\",\n  \"redact_pii_audio\": true,\n  \"redact_pii_audio_quality\": \"<string>\",\n  \"filter_profanity\": true,\n  \"word_boost\": [\n    \"<string>\"\n  ],\n  \"boost_param\": \"<string>\",\n  \"custom_spelling\": [\n    {}\n  ],\n  \"webhook_url\": \"<string>\",\n  \"multichannel\": true,\n  \"audio_start_from\": 123,\n  \"audio_end_at\": 123,\n  \"custom_topics\": true,\n  \"topics\": [\n    \"<string>\"\n  ]\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "<authorization>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://mavi-backend.memories.ai/serve/api/v2/transcriptions/speech-to-text")
  .header("Authorization", "<authorization>")
  .header("Content-Type", "application/json")
  .body("{\n  \"provider\": \"<string>\",\n  \"asset_id\": \"<string>\",\n  \"url\": \"<string>\",\n  \"source_url\": \"<string>\",\n  \"language_code\": \"<string>\",\n  \"punctuate\": true,\n  \"format_text\": true,\n  \"speaker_labels\": true,\n  \"speakers_expected\": 123,\n  \"language_detection\": true,\n  \"language_confidence_threshold\": 123,\n  \"speech_model\": \"<string>\",\n  \"speech_threshold\": 123,\n  \"disfluencies\": true,\n  \"sentiment_analysis\": true,\n  \"entity_detection\": true,\n  \"auto_highlights\": true,\n  \"content_safety\": true,\n  \"iab_categories\": true,\n  \"auto_chapters\": true,\n  \"summarization\": true,\n  \"summary_model\": \"<string>\",\n  \"summary_type\": \"<string>\",\n  \"redact_pii\": true,\n  \"redact_pii_policies\": [\n    \"<string>\"\n  ],\n  \"redact_pii_sub\": \"<string>\",\n  \"redact_pii_audio\": true,\n  \"redact_pii_audio_quality\": \"<string>\",\n  \"filter_profanity\": true,\n  \"word_boost\": [\n    \"<string>\"\n  ],\n  \"boost_param\": \"<string>\",\n  \"custom_spelling\": [\n    {}\n  ],\n  \"webhook_url\": \"<string>\",\n  \"multichannel\": true,\n  \"audio_start_from\": 123,\n  \"audio_end_at\": 123,\n  \"custom_topics\": true,\n  \"topics\": [\n    \"<string>\"\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://mavi-backend.memories.ai/serve/api/v2/transcriptions/speech-to-text")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = '<authorization>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"provider\": \"<string>\",\n  \"asset_id\": \"<string>\",\n  \"url\": \"<string>\",\n  \"source_url\": \"<string>\",\n  \"language_code\": \"<string>\",\n  \"punctuate\": true,\n  \"format_text\": true,\n  \"speaker_labels\": true,\n  \"speakers_expected\": 123,\n  \"language_detection\": true,\n  \"language_confidence_threshold\": 123,\n  \"speech_model\": \"<string>\",\n  \"speech_threshold\": 123,\n  \"disfluencies\": true,\n  \"sentiment_analysis\": true,\n  \"entity_detection\": true,\n  \"auto_highlights\": true,\n  \"content_safety\": true,\n  \"iab_categories\": true,\n  \"auto_chapters\": true,\n  \"summarization\": true,\n  \"summary_model\": \"<string>\",\n  \"summary_type\": \"<string>\",\n  \"redact_pii\": true,\n  \"redact_pii_policies\": [\n    \"<string>\"\n  ],\n  \"redact_pii_sub\": \"<string>\",\n  \"redact_pii_audio\": true,\n  \"redact_pii_audio_quality\": \"<string>\",\n  \"filter_profanity\": true,\n  \"word_boost\": [\n    \"<string>\"\n  ],\n  \"boost_param\": \"<string>\",\n  \"custom_spelling\": [\n    {}\n  ],\n  \"webhook_url\": \"<string>\",\n  \"multichannel\": true,\n  \"audio_start_from\": 123,\n  \"audio_end_at\": 123,\n  \"custom_topics\": true,\n  \"topics\": [\n    \"<string>\"\n  ]\n}"

response = http.request(request)
puts response.read_body

{
  "code": 200,
  "msg": "success",
  "data": {
    "id": "9a27d0d5-d2db-448c-823c-f098507789be",
    "status": "completed",
    "language_code": "en_us",
    "audio_url": "https://storage.googleapis.com/...",
    "audio_duration": 52,
    "text": "Hello, how are you today? I'm doing well, thank you.",
    "words": [
      {
        "text": "Hello,",
        "start": 0,
        "end": 520,
        "confidence": 0.99,
        "speaker": "A"
      },
      {
        "text": "how",
        "start": 520,
        "end": 780,
        "confidence": 0.98,
        "speaker": "A"
      }
    ],
    "utterances": [
      {
        "confidence": 0.97,
        "start": 0,
        "end": 2980,
        "text": "Hello, how are you today?",
        "speaker": "A"
      },
      {
        "confidence": 0.95,
        "start": 2980,
        "end": 5200,
        "text": "I'm doing well, thank you.",
        "speaker": "B"
      }
    ],
    "confidence": 0.97,
    "punctuate": true,
    "format_text": true,
    "speaker_labels": true,
    "speakers_expected": 2
  },
  "failed": false,
  "success": true
}

Product: Visual Intelligence — Audio File Transcription Use case: Transcribe an uploaded audio/video file to text — async batch or sync, multiple providers (Whisper, ElevenLabs, AssemblyAI) with optional speaker labels. For live streams, see Live Audio Transcription. Host: https://mavi-backend.memories.ai/serve/api/v2 Auth: Authorization: sk-mavi-... (no Bearer prefix)

Uses AssemblyAI Universal-2 model. Submits a job and polls until completion, then returns the full result.

Pricing: $0.15/hour of audio, billed by actual audio duration (in seconds).

Audio Source

You must provide one of the following (priority: asset_id > url > source_url).

Parameters

Authorization

string

required

API key for authentication (e.g. sk-mavi-...).

provider

string

required

STT provider. Must be assemblyai.

asset_id

string

The unique identifier of an uploaded audio/video asset (e.g. re_xxx). Resolved to a signed GCS URL.

url

string

A publicly accessible audio URL.

source_url

string

A gs:// GCS path or public HTTP URL. GCS paths are converted to signed URLs automatically.

language_code

string

Language code (ISO 639-1, e.g. en, zh). If omitted, the provider auto-detects the language.

punctuate

boolean

default:"true"

Add punctuation.

format_text

boolean

default:"true"

Format numbers, dates, etc.

speaker_labels

boolean

Enable speaker diarization.

speakers_expected

integer

Expected number of speakers.

language_detection

boolean

Enable automatic language detection.

language_confidence_threshold

number

Confidence threshold for language detection (0.0–1.0).

speech_model

string

Speech recognition model to use.

speech_threshold

number

Speech confidence threshold (0.0–1.0).

disfluencies

boolean

Include disfluencies (um, uh, etc.).

sentiment_analysis

boolean

Enable sentiment analysis per utterance.

entity_detection

boolean

Enable entity detection (names, locations, etc.).

auto_highlights

boolean

Automatically highlight key phrases.

content_safety

boolean

Enable content safety detection.

iab_categories

boolean

Enable IAB topic categorization.

auto_chapters

boolean

Automatically generate chapters.

summarization

boolean

Enable summarization.

summary_model

string

Summarization model: informative or conversational.

summary_type

string

Summary format: bullets, bullets_verbose, headline, paragraph, or gist.

redact_pii

boolean

Enable PII redaction.

redact_pii_policies

string[]

PII types to redact (e.g. email_address, phone_number, person_name).

redact_pii_sub

string

PII replacement strategy: hash or entity_name.

redact_pii_audio

boolean

Redact PII from audio output.

redact_pii_audio_quality

string

Redacted audio quality: mp3 or wav.

filter_profanity

boolean

Filter profanity from transcript.

word_boost

string[]

List of words to boost recognition.

boost_param

string

Boost strength: low, default, or high.

custom_spelling

object[]

Custom spelling corrections.

webhook_url

string

AssemblyAI webhook callback URL.

multichannel

boolean

Enable multi-channel transcription.

audio_start_from

integer

Start transcription from this time (milliseconds).

audio_end_at

integer

End transcription at this time (milliseconds).

custom_topics

boolean

Enable custom topic detection.

topics

string[]

Custom topic labels.

Code Examples

curl --request POST \
  --url https://mavi-backend.memories.ai/serve/api/v2/transcriptions/speech-to-text \
  --header 'Authorization: sk-mavi-...' \
  --header 'Content-Type: application/json' \
  --data '{
    "provider": "assemblyai",
    "asset_id": "re_657929111888723968",
    "language_code": "en",
    "speaker_labels": true,
    "speakers_expected": 2,
    "punctuate": true,
    "format_text": true
  }'

const BASE_URL = "https://mavi-backend.memories.ai/serve/api/v2/transcriptions";
const API_KEY = "sk-mavi-...";

const response = await fetch(`${BASE_URL}/speech-to-text`, {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Authorization': API_KEY
  },
  body: JSON.stringify({
    provider: 'assemblyai',
    asset_id: 're_657929111888723968',
    language_code: 'en',
    speaker_labels: true,
    speakers_expected: 2,
    punctuate: true,
    format_text: true
  })
});

const data = await response.json();
console.log(data);

import requests

BASE_URL = "https://mavi-backend.memories.ai/serve/api/v2/transcriptions"
API_KEY = "sk-mavi-..."
HEADERS = {
    "Authorization": API_KEY,
    "Content-Type": "application/json"
}

response = requests.post(f"{BASE_URL}/speech-to-text", json={
    "provider": "assemblyai",
    "asset_id": "re_657929111888723968",
    "language_code": "en",
    "speaker_labels": True,
    "speakers_expected": 2,
    "punctuate": True,
    "format_text": True
}, headers=HEADERS)

print(response.json())

Response

{
  "code": 200,
  "msg": "success",
  "data": {
    "id": "9a27d0d5-d2db-448c-823c-f098507789be",
    "status": "completed",
    "language_code": "en_us",
    "audio_url": "https://storage.googleapis.com/...",
    "audio_duration": 52,
    "text": "Hello, how are you today? I'm doing well, thank you.",
    "words": [
      {
        "text": "Hello,",
        "start": 0,
        "end": 520,
        "confidence": 0.99,
        "speaker": "A"
      },
      {
        "text": "how",
        "start": 520,
        "end": 780,
        "confidence": 0.98,
        "speaker": "A"
      }
    ],
    "utterances": [
      {
        "confidence": 0.97,
        "start": 0,
        "end": 2980,
        "text": "Hello, how are you today?",
        "speaker": "A"
      },
      {
        "confidence": 0.95,
        "start": 2980,
        "end": 5200,
        "text": "I'm doing well, thank you.",
        "speaker": "B"
      }
    ],
    "confidence": 0.97,
    "punctuate": true,
    "format_text": true,
    "speaker_labels": true,
    "speakers_expected": 2
  },
  "failed": false,
  "success": true
}

Response Parameters

Parameter	Type	Description
data.id	string	AssemblyAI transcript ID
data.status	string	Transcript status: `completed`
data.language_code	string	Detected language code
data.audio_duration	integer	Audio duration in seconds
data.text	string	Full transcription text
data.confidence	number	Overall transcription confidence (0.0–1.0)
data.words	array[object]	Word-level transcription with timing (milliseconds)
data.words[].text	string	The transcribed word
data.words[].start	integer	Start time in milliseconds
data.words[].end	integer	End time in milliseconds
data.words[].confidence	number	Word confidence score
data.words[].speaker	string	Speaker label (e.g. `A`, `B`). Only present when `speaker_labels=true`.
data.utterances	array[object]	Sentence-level segments (only when `speaker_labels=true`)
data.utterances[].text	string	Utterance text
data.utterances[].start	integer	Start time in milliseconds
data.utterances[].end	integer	End time in milliseconds
data.utterances[].confidence	number	Utterance confidence score
data.utterances[].speaker	string	Speaker label

Timestamps are in milliseconds (e.g. 520).

ElevenLabs Whisper Audio Transcription

Get Started

Asset Management

Social Media Scraping

Audio File Transcription

Live Audio Transcription

Video Model APIs

Video Task APIs

Live Video Content Moderation

Live Video Understanding

Image Model APIs

Embeddings

Human ReID & Caption

Reference

Audio Source

Parameters

Code Examples

Response

Response Parameters

​Audio Source

​Parameters

​Code Examples

​Response

​Response Parameters

Audio Source

Parameters

Code Examples

Response

Response Parameters