universal

This documentation is valid for the following list of our models:

• aai/universal

Try in Playground

A new Speech-to-Text model offering exceptional accuracy by leveraging its deep understanding of context and semantics, with the broadest language support.

This model use per-second billing. The cost of audio transcription is based on the number of seconds in the input audio file, not the processing time.

Setup your API Key

If you don’t have an API key for the AI/ML API yet, feel free to use our Quickstart guide.

API Schemas

Creating and sending a speech-to-text conversion task to the server

post

Body

application/json

modelstring · enumRequiredPossible values:

urlstring · uriOptional

URL of the input audio file.

audio_start_frominteger · nullableOptional

The point in time, in milliseconds, in the file at which the transcription was started.

audio_end_atinteger · nullableOptional

The point in time, in milliseconds, in the file at which the transcription was terminated.

language_codestringOptional

The language of your audio file. Possible values are found in Supported Languages. The default value is 'en_us'.

language_confidence_thresholdnumber · max: 1 · nullableOptional

The confidence threshold for the automatically detected language. An error will be returned if the language confidence is below this threshold. Defaults to 0.

language_detectionboolean · nullableOptional

Enable Automatic language detection, either true or false. Available for universal model only.

punctuateboolean · nullableOptional

Adds punctuation and capitalization to the transcript

Default: null

format_textboolean · nullableOptional

Enable Text Formatting, can be true or false.

Default: true

disfluenciesboolean · nullableOptional

Transcribe Filler Words, like "umm", in your media file; can be true or false.

Default: false

multichannelboolean · nullableOptional

Enable Multichannel transcription, can be true or false.

Default: false

speaker_labelsboolean · nullableOptional

Enable Speaker diarization, can be true or false.

Default: null

speakers_expectedinteger · nullableOptional

Tell the speaker label model how many speakers it should attempt to identify. See Speaker diarization for more details.

Default: null

content_safetyboolean · nullableOptional

Enable Content Moderation, can be true or false.

Default: false

iab_categoriesboolean · nullableOptional

Enable Topic Detection, can be true or false.

Default: false

auto_highlightsboolean · nullableOptional

Enable Key Phrases, either true or false.

Default: false

word_booststring[]Optional

The list of custom vocabulary to boost transcription probability for.

boost_paramstring · enumOptional

How much to boost specified words. Allowed values: low, default, high.

Possible values:

filter_profanityboolean · nullableOptional

Filter profanity from the transcribed text, can be true or false.

Default: false

redact_piiboolean · nullableOptional

Redact PII from the transcribed text using the Redact PII model, can be true or false.

Default: false

redact_pii_audioboolean · nullableOptional

Generate a copy of the original media file with spoken PII "beeped" out, can be true or false. See PII redaction for more details.

Default: false

redact_pii_audio_qualitystring · enumOptional

Controls the filetype of the audio created by redact_pii_audio. Currently supports mp3 (default) and wav. See PII redaction for more details.

Possible values:

redact_pii_substring · enumOptional

The replacement logic for detected PII, can be entity_type or hash. See PII redaction for more details.

Possible values:

sentiment_analysisboolean · nullableOptional

Enable Sentiment Analysis, can be true or false.

Default: false

entity_detectionboolean · nullableOptional

Enable Entity Detection, can be true or false.

Default: false

summarizationboolean · nullableOptional

Enable Summarization, can be true or false.

Default: false

summary_modelstring · enumOptional

The model to summarize the transcript. Allowed values: informative, conversational, catchy.

Possible values:

summary_typestring · enumOptional

The type of summary. Allowed values: bullets, bullets_verbose, gist, headline, paragraph.

Possible values:

auto_chaptersboolean · nullableOptional

Enable Auto Chapters, either true or false.

Default: false

speech_thresholdnumber · max: 1 · nullableOptional

Reject audio files that contain less than this fraction of speech. Valid values are in the range [0, 1] inclusive.

Responses

200Success

application/json

generation_idstringRequired

post

/v1/stt/create

cURLJavaScriptPython

curl -L \
  --request POST \
  --url 'https://api.aimlapi.com/v1/stt/create' \
  --header 'Authorization: Bearer <YOUR_AIMLAPI_KEY>' \
  --header 'Content-Type: application/json' \
  --data '{
      "model": "aai/universal",
      "url": "https://audio-samples.github.io/samples/mp3/blizzard_primed/sample-0.mp3"
    }'

200Success

{
  "generation_id": "text"
}

Requesting the result of the task from the server using the generation_id

get

Path parameters

generation_idstringRequired

Responses

200Success

application/json

idstringRequired

statusstring · enumRequiredPossible values:

outputany ofRequired

or

or

get

/v1/stt/{generation_id}

HTTPcURLJavaScriptPython

GET /v1/stt/{generation_id} HTTP/1.1
Host: api.aimlapi.com
Accept: */*

200Success

{
  "id": "text",
  "status": "queued",
  "output": {
    "metadata": {
      "transaction_key": "text",
      "request_id": "text",
      "sha256": "text",
      "created": "2026-05-21T00:53:06.796Z",
      "duration": 1,
      "channels": 1,
      "models": [
        "text"
      ],
      "model_info": {
        "ANY_ADDITIONAL_PROPERTY": {
          "name": "text",
          "version": "text",
          "arch": "text"
        }
      }
    },
    "results": {
      "channels": {
        "alternatives": [
          {
            "transcript": "text",
            "confidence": 1,
            "words": [
              {
                "word": "text",
                "start": 1,
                "end": 1,
                "confidence": 1,
                "punctuated_word": "text"
              }
            ],
            "paragraphs": [
              {
                "transcript": "text",
                "paragraphs": {
                  "sentences": [
                    {
                      "text": "text",
                      "start": 1,
                      "end": 1
                    }
                  ],
                  "num_words": 1,
                  "start": 1,
                  "end": 1
                }
              }
            ]
          }
        ]
      }
    }
  },
  "error": {
    "name": "text",
    "message": "text"
  }
}

Quick Example: Processing a Speech Audio File via URL

Let's transcribe the following audio fragment:

import time
import requests
import json   # for getting a structured output with indentation

base_url = "https://api.aimlapi.com/v1"
# Insert your AIML API Key instead of <YOUR_AIMLAPI_KEY>:
api_key = "<YOUR_AIMLAPI_KEY>"

# Creating and sending a speech-to-text conversion task to the server
def create_stt():
    url = f"{base_url}/stt/create"
    headers = {
        "Authorization": f"Bearer {api_key}", 
    }

    data = {
        "model": "aai/universal",
        "url": "https://audio-samples.github.io/samples/mp3/blizzard_primed/sample-0.mp3"
    }
 
    response = requests.post(url, json=data, headers=headers)
    
    if response.status_code >= 400:
        print(f"Error: {response.status_code} - {response.text}")
    else:
        response_data = response.json()
        print(response_data)
        return response_data

# Requesting the result of the task from the server using the generation_id
def get_stt(gen_id):
    url = f"{base_url}/stt/{gen_id}"
    headers = {
        "Authorization": f"Bearer {api_key}", 
    }
    response = requests.get(url, headers=headers)
    return response.json()
    
# First, start the generation, then repeatedly request the result from the server every 10 seconds.
def main():
    stt_response = create_stt()
    gen_id = stt_response.get("generation_id")



    if gen_id:
        start_time = time.time()

        timeout = 600
        while time.time() - start_time < timeout:
            response_data = get_stt(gen_id)

            if response_data is None:
                print("Error: No response from API")
                break
        
            status = response_data.get("status")

            if status == "waiting" or status == "active":
                print("Still waiting... Checking again in 10 seconds.")
                time.sleep(10)
            else:
                
                print("Processing complete:\n", response_data["result"]["text"])
                
                # Uncomment the line below to print the entire "result" object with all service data
                # print("Processing complete:\n", json.dumps(response_data["result"], indent=2, ensure_ascii=False))
                return response_data
   
        print("Timeout reached. Stopping.")
        return None     


if __name__ == "__main__":
    main()

Response

{'generation_id': '0cff4e24-c1ba-419d-8b62-46f342985881'}
Still waiting... Checking again in 10 seconds.
Processing complete:\n {
  "id": "04d07a4c-9238-4860-ac6f-534d58fdaf9a",
  "language_model": "assemblyai_default",
  "acoustic_model": "assemblyai_default",
  "language_code": "en_us",
  "status": "completed",
  "audio_url": "https://audio-samples.github.io/samples/mp3/blizzard_primed/sample-0.mp3",
  "text": "He doesn't belong to you. And I don't see how you have anything to do with what is be his power yet his he presumably that from this stage to you be fired.",
  "words": [
    {
      "text": "He",
      "start": 400,
      "end": 520,
      "confidence": 0.98876953,
      "speaker": null
    },
    {
      "text": "doesn't",
      "start": 520,
      "end": 880,
      "confidence": 0.9296875,
      "speaker": null
    },
    {
      "text": "belong",
      "start": 880,
      "end": 1320,
      "confidence": 1,
      "speaker": null
    },
    {
      "text": "to",
      "start": 1320,
      "end": 1560,
      "confidence": 0.99853516,
      "speaker": null
    },
    {
      "text": "you.",
      "start": 1560,
      "end": 1840,
      "confidence": 0.99853516,
      "speaker": null
    },
    {
      "text": "And",
      "start": 1840,
      "end": 2120,
      "confidence": 0.99365234,
      "speaker": null
    },
    {
      "text": "I",
      "start": 2120,
      "end": 2280,
      "confidence": 0.99902344,
      "speaker": null
    },
    {
      "text": "don't",
      "start": 2280,
      "end": 2520,
      "confidence": 0.9949544,
      "speaker": null
    },
    {
      "text": "see",
      "start": 2520,
      "end": 2720,
      "confidence": 0.99902344,
      "speaker": null
    },
    {
      "text": "how",
      "start": 2720,
      "end": 3000,
      "confidence": 0.99902344,
      "speaker": null
    },
    {
      "text": "you",
      "start": 3000,
      "end": 3320,
      "confidence": 0.99853516,
      "speaker": null
    },
    {
      "text": "have",
      "start": 3320,
      "end": 3600,
      "confidence": 0.99658203,
      "speaker": null
    },
    {
      "text": "anything",
      "start": 3600,
      "end": 4080,
      "confidence": 0.9968262,
      "speaker": null
    },
    {
      "text": "to",
      "start": 4080,
      "end": 4240,
      "confidence": 0.99902344,
      "speaker": null
    },
    {
      "text": "do",
      "start": 4240,
      "end": 4360,
      "confidence": 0.99902344,
      "speaker": null
    },
    {
      "text": "with",
      "start": 4360,
      "end": 4520,
      "confidence": 0.9902344,
      "speaker": null
    },
    {
      "text": "what",
      "start": 4520,
      "end": 4720,
      "confidence": 0.9941406,
      "speaker": null
    },
    {
      "text": "is",
      "start": 4720,
      "end": 4920,
      "confidence": 0.9819336,
      "speaker": null
    },
    {
      "text": "be",
      "start": 4920,
      "end": 5080,
      "confidence": 0.8720703,
      "speaker": null
    },
    {
      "text": "his",
      "start": 5080,
      "end": 5280,
      "confidence": 0.9951172,
      "speaker": null
    },
    {
      "text": "power",
      "start": 5280,
      "end": 5520,
      "confidence": 0.8588867,
      "speaker": null
    },
    {
      "text": "yet",
      "start": 5520,
      "end": 5840,
      "confidence": 0.5756836,
      "speaker": null
    },
    {
      "text": "his",
      "start": 5840,
      "end": 6160,
      "confidence": 0.5419922,
      "speaker": null
    },
    {
      "text": "he",
      "start": 6160,
      "end": 6360,
      "confidence": 0.96972656,
      "speaker": null
    },
    {
      "text": "presumably",
      "start": 6360,
      "end": 6840,
      "confidence": 0.5012207,
      "speaker": null
    },
    {
      "text": "that",
      "start": 6840,
      "end": 7000,
      "confidence": 0.8901367,
      "speaker": null
    },
    {
      "text": "from",
      "start": 7000,
      "end": 7160,
      "confidence": 0.9951172,
      "speaker": null
    },
    {
      "text": "this",
      "start": 7160,
      "end": 7320,
      "confidence": 0.9926758,
      "speaker": null
    },
    {
      "text": "stage",
      "start": 7320,
      "end": 7680,
      "confidence": 0.9953613,
      "speaker": null
    },
    {
      "text": "to",
      "start": 7680,
      "end": 7960,
      "confidence": 0.9941406,
      "speaker": null
    },
    {
      "text": "you",
      "start": 7960,
      "end": 8320,
      "confidence": 0.9975586,
      "speaker": null
    },
    {
      "text": "be",
      "start": 9440,
      "end": 9720,
      "confidence": 0.4555664,
      "speaker": null
    },
    {
      "text": "fired.",
      "start": 9720,
      "end": 10050,
      "confidence": 0.4534912,
      "speaker": null
    }
  ],
  "utterances": null,
  "confidence": 0.90746206,
  "audio_duration": 11,
  "punctuate": true,
  "format_text": true,
  "dual_channel": null,
  "webhook_url": null,
  "webhook_status_code": null,
  "webhook_auth": false,
  "webhook_auth_header_name": null,
  "speed_boost": false,
  "auto_highlights_result": null,
  "auto_highlights": false,
  "audio_start_from": null,
  "audio_end_at": null,
  "word_boost": [],
  "boost_param": null,
  "prompt": null,
  "keyterms_prompt": [],
  "filter_profanity": false,
  "redact_pii": false,
  "redact_pii_audio": false,
  "redact_pii_audio_quality": null,
  "redact_pii_audio_options": null,
  "redact_pii_policies": null,
  "redact_pii_sub": null,
  "speaker_labels": false,
  "speaker_options": null,
  "content_safety": false,
  "iab_categories": false,
  "content_safety_labels": {
    "status": "unavailable",
    "results": [],
    "summary": {}
  },
  "iab_categories_result": {
    "status": "unavailable",
    "results": [],
    "summary": {}
  },
  "language_detection": false,
  "language_detection_options": null,
  "language_confidence_threshold": null,
  "language_confidence": null,
  "custom_spelling": null,
  "throttled": false,
  "auto_chapters": false,
  "summarization": false,
  "summary_type": null,
  "summary_model": null,
  "custom_topics": false,
  "topics": [],
  "speech_threshold": null,
  "speech_model": "universal",
  "chapters": null,
  "disfluencies": false,
  "entity_detection": false,
  "sentiment_analysis": false,
  "sentiment_analysis_results": null,
  "entities": null,
  "speakers_expected": null,
  "summary": null,
  "custom_topics_results": null,
  "is_deleted": null,
  "multichannel": null,
  "project_id": 675898,
  "token_id": 1245789
}