nova-2

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

• #g1_nova-2-automotive

• #g1_nova-2-conversationalai

• #g1_nova-2-drivethru

• #g1_nova-2-finance

• #g1_nova-2-general

• #g1_nova-2-medical

• #g1_nova-2-meeting

• #g1_nova-2-phonecall

• #g1_nova-2-video

• #g1_nova-2-voicemail

Model Overview

Nova-2 builds on the advancements of Nova-1 with speech-specific optimizations to its Transformer architecture, refined data curation techniques, and a multi-stage training approach. These improvements result in a lower word error rate (WER) and better entity recognition (including proper nouns and alphanumeric sequences), as well as enhanced punctuation and capitalization.

Nova-2 offers the following model options:

• automotive: Optimized for audio with automotive oriented vocabulary.

• conversationalai: Optimized for use cases in which a human is talking to an automated bot, such as IVR, a voice assistant, or an automated kiosk.

• drivethru: Optimized for audio sources from drivethrus.

• finance: Optimized for multiple speakers with varying audio quality, such as might be found on a typical earnings call. Vocabulary is heavily finance oriented.

• general: Optimized for everyday audio processing.

• medical: Optimized for audio with medical oriented vocabulary.

• meeting: Optimized for conference room settings, which include multiple speakers with a single microphone.

• phonecall: Optimized for low-bandwidth audio phone calls.

• video: Optimized for audio sourced from videos.

• voicemail: Optimized for low-bandwidth audio clips with a single speaker. Derived from the phonecall model.

Nova-2 models 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

custom_intentany ofOptional

A custom intent you want the model to detect within your input audio if present. Submit up to 100.

stringOptional

or

string[]Optional

custom_topicany ofOptional

A custom topic you want the model to detect within your input audio if present. Submit up to 100.

stringOptional

or

string[]Optional

custom_intent_modestring · enumOptional

Sets how the model will interpret strings submitted to the custom_intent param. When strict, the model will only return intents submitted using the custom_intent param. When extended, the model will return its own detected intents in addition those submitted using the custom_intents param.

Possible values:

custom_topic_modestring · enumOptional

Sets how the model will interpret strings submitted to the custom_topic param. When strict, the model will only return topics submitted using the custom_topic param. When extended, the model will return its own detected topics in addition to those submitted using the custom_topic param.

Possible values:

detect_languageboolean · nullableOptional

Enables language detection to identify the dominant language spoken in the submitted audio.

detect_entitiesboolean · nullableOptional

When Entity Detection is enabled, the Punctuation feature will be enabled by default.

detect_topicsboolean · nullableOptional

Detects the most important and relevant topics that are referenced in speech within the audio.

diarizeboolean · nullableOptional

Recognizes speaker changes. Each word in the transcript will be assigned a speaker number starting at 0.

dictationboolean · nullableOptional

Identifies and extracts key entities from content in submitted audio.

diarize_versionstringOptional

extrastringOptional

Arbitrary key-value pairs that are attached to the API response for usage in downstream processing.

filler_wordsboolean · nullableOptional

Filler Words can help transcribe interruptions in your audio, like “uh” and “um”.

intentsboolean · nullableOptional

Recognizes speaker intent throughout a transcript or text.

keywordsstringOptional

Keywords can boost or suppress specialized terminology and brands.

languagestringOptional

The BCP-47 language tag that hints at the primary spoken language. Depending on the Model and API endpoint you choose only certain languages are available

measurementsboolean · nullableOptional

Spoken measurements will be converted to their corresponding abbreviations

multi_channelboolean · nullableOptional

Transcribes each audio channel independently

numeralsboolean · nullableOptional

Numerals converts numbers from written format to numerical format

paragraphsboolean · nullableOptional

Splits audio into paragraphs to improve transcript readability

profanity_filterboolean · nullableOptional

Profanity Filter looks for recognized profanity and converts it to the nearest recognized non-profane word or removes it from the transcript completely

punctuateboolean · nullableOptional

Adds punctuation and capitalization to the transcript

searchstringOptional

Search for terms or phrases in submitted audio

sentimentboolean · nullableOptional

Recognizes the sentiment throughout a transcript or text

smart_formatboolean · nullableOptional

Applies formatting to transcript output. When set to true, additional formatting will be applied to transcripts to improve readability

summarizestringOptional

Summarizes content. For Listen API, supports string version option. For Read API, accepts boolean only.

tagstring[]Optional

Labels your requests for the purpose of identification during usage reporting

topicsboolean · nullableOptional

Detects topics throughout a transcript or text

utterancesboolean · nullableOptional

Segments speech into meaningful semantic units

utt_splitnumberOptional

Seconds to wait before detecting a pause between words in submitted audio

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": "#g1_nova-2-automotive",
      "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": "2026-06-10T15:27:11.220Z",
      "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 Code Examples

Let's use the #g1_nova-2-meeting model to transcribe the following audio fragment:

Example #1: Processing a Speech Audio File via URL

import time
import requests

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": "#g1_nova-2-meeting",
        "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"]['results']["channels"][0]["alternatives"][0]["transcript"])
                return response_data
   
        print("Timeout reached. Stopping.")
        return None     


if __name__ == "__main__":
    main()

Response

{'generation_id': 'h66460ba-0562-1dd9-b440-a56d947e72a3'}
Processing complete:
 He doesn't belong to you and i don't see how you have anything to do with what is be his power yet he's he persona from this stage to you be fine

Example #2: Processing a Speech Audio File via File Path

import time
import requests

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": "#g1_nova-2-meeting",
    }
    with open("stt-sample.mp3", "rb") as file:
        files = {"audio": ("sample.mp3", file, "audio/mpeg")}
        response = requests.post(url, data=data, headers=headers, files=files)
    
    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"]['results']["channels"][0]["alternatives"][0]["transcript"])
                return response_data
   
        print("Timeout reached. Stopping.")
        return None     


if __name__ == "__main__":
    main()

Response

{'generation_id': 'd793a81c-f8d8-40e0-a7c6-049ec6f54446'}
Processing complete:
 He doesn't belong to you, and I don't see how you have anything to do with what is be his power yet. He's he pursuing that from this stage to you.