MAI-Transcribe 1.5

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

microsoft/mai-transcribe-1.5

Model Overview

MAI-Transcribe 1.5 — speech-to-text model from Microsoft. Supports multilingual transcription, automatic language detection, and punctuation restoration.

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

modelstring · enumRequiredPossible values:

urlstring · uriOptional

URL of the input audio file. Provide either url or audio — exactly one is required, not both.

Example: https://example.com/audio/sample.mp3

audiostring · binaryOptional

The audio file to transcribe. Provide either url or audio — exactly one is required, not both.

max_tokensinteger · min: 1Optional

The maximum number of tokens that can be generated in the chat completion. This value can be used to control costs for text generated via API.

Example: 4096

temperaturenumber · max: 2Optional

What sampling temperature to use. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both.

Default: 1Example: 1

top_pnumber · max: 1Optional

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.

Default: 1Example: 1

max_completion_tokensinteger · min: 1Optional

An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens.

Example: 4096

Responses

200Success

application/json

generation_idstringRequired

post

/v1/stt/create

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": "microsoft/mai-transcribe-1.5",
      "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

get

/v1/stt/{generation_id}

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": "2026-06-10T14:48:15.933Z",
      "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"
  }
}

Code Example: Processing a Speech Audio File via URL

Let's use the microsoft/mai-transcribe-1.5 model to transcribe the following audio fragment:

import requests
import time
import json

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

# Create and send 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": "microsoft/mai-transcribe-1.5",
        "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

# Request 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()

# Start the generation, then repeatedly request the result from the server every 10 sec.
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 in ["queued", "generating"]:
                print(f"Status: {status}. Checking again in 10 seconds.")
                time.sleep(10)
            else:
                print("Processing complete:")
                print(json.dumps(response_data["result"], indent=2, ensure_ascii=False))
                return response_data

        print("Timeout reached. Stopping.")
        return None


if __name__ == "__main__":
    main()

const baseUrl = "https://api.aimlapi.com/v1";
// Insert your AIML API Key instead of <YOUR_AIMLAPI_KEY>:
const apiKey = "<YOUR_AIMLAPI_KEY>";

// Create and send a speech-to-text conversion task to the server
async function createSTT() {
  const url = `${baseUrl}/stt/create`;

  const response = await fetch(url, {
    method: "POST",
    headers: {
      "Authorization": `Bearer ${apiKey}`,
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      model: "microsoft/mai-transcribe-1.5",
      url: "https://audio-samples.github.io/samples/mp3/blizzard_primed/sample-0.mp3",
    }),
  });

  if (!response.ok) {
    const text = await response.text();
    console.error(`Error: ${response.status} - ${text}`);
    return null;
  }

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

// Request the result of the task from the server using the generation_id
async function getSTT(genId) {
  const url = `${baseUrl}/stt/${genId}`;

  const response = await fetch(url, {
    headers: {
      "Authorization": `Bearer ${apiKey}`,
    },
  });

  if (!response.ok) {
    return null;
  }

  return response.json();
}

// Start generation and poll every 10s
async function main() {
  const sttResponse = await createSTT();
  const genId = sttResponse?.generation_id;

  if (!genId) {
    console.error("No generation_id received");
    return null;
  }

  const startTime = Date.now();
  const timeoutMs = 600 * 1000; // 10 minutes

  while (Date.now() - startTime < timeoutMs) {
    const responseData = await getSTT(genId);

    if (!responseData) {
      console.error("Error: No response from API");
      return null;
    }

    const status = responseData.status;

    if (status === "queued" || status === "generating") {
      console.log(`Status: ${status}. Checking again in 10 seconds.`);
      await new Promise(resolve => setTimeout(resolve, 10_000));
    } else {
      console.log("Processing complete:");
      console.log(JSON.stringify(responseData.result, null, 2));
      return responseData;
    }
  }

  console.log("Timeout reached. Stopping.");
  return null;
}

main();

Response

{'generation_id': 'XY3D-mYpFxC-WIx-Lv3wh', 'status': 'queued'}
Status: queued. Checking again in 10 seconds.
Processing complete:
{
  "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. He's he is only that from this stage to you.",
  "usage": {
    "seconds": 11,
    "cost": 0.0011
  }
}

PreviousMicrosoft NextText-to-Speech

Last updated 6 days ago

Was this helpful?