# Speech-to-Text ## Overview Speech-to-text models convert spoken language into written text, enabling voice-based interactions across various applications. These models leverage deep learning techniques, such as recurrent neural networks (RNNs) and transformers, to process audio signals and transcribe them with high accuracy. They are commonly used in voice assistants, transcription services, and accessibility tools, supporting multiple languages and adapting to different accents and speech patterns. {% hint style="warning" %} Generated audio transcriptions are stored on the server for 1 hour from the time of creation. {% endhint %} ## Quick Code Examples Let's use the `#g1_whisper-large` model to transcribe the following audio fragment: {% embed url="" %} ### 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_whisper-large",
        "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":
                ("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 {% code overflow="wrap" %} ``` {'generation_id': 'e3d46bba-7562-44a9-b440-504d940342a3'} 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 personified from this stage to you be fire ``` {% endcode %}
### Example #2: Processing a Speech Audio File via File Path {% code overflow="wrap" %} ```python import time import requests base_url = "https://api.aimlapi.com/v1" # Insert your AIML API Key instead of : api_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_whisper-large", } 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() ``` {% endcode %}
Response {% code overflow="wrap" %} ```lisp {'generation_id': 'dd412e9d-044c-43ae-b97b-e920755074d5'} 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 personified from this stage to you be fire ``` {% endcode %}
## All Available Speech-to-Text Models
Model ID + API Reference linkDeveloperContextModel Card
aai/slam-1Assembly AISlam 1
aai/universalAssembly AIUniversal
#g1_nova-2-automotiveDeepgramDeepgram Nova-2
#g1_nova-2-conversationalaiDeepgramDeepgram Nova-2
#g1_nova-2-drivethruDeepgramDeepgram Nova-2
#g1_nova-2-financeDeepgramDeepgram Nova-2
#g1_nova-2-generalDeepgramDeepgram Nova-2
#g1_nova-2-medicalDeepgramDeepgram Nova-2
#g1_nova-2-meetingDeepgramDeepgram Nova-2
#g1_nova-2-phonecallDeepgramDeepgram Nova-2
#g1_nova-2-videoDeepgramDeepgram Nova-2
#g1_nova-2-voicemailDeepgramDeepgram Nova-2
#g1_whisper-tinyOpenAI-
#g1_whisper-smallOpenAI-
#g1_whisper-baseOpenAI-
#g1_whisper-mediumOpenAI-
#g1_whisper-largeOpenAIWhisper
openai/gpt-4o-transcribeOpenAIGPT-4o Transcribe
openai/gpt-4o-mini-transcribeOpenAIGPT-4o Mini Transcribe
--- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.aimlapi.com/api-references/speech-models/speech-to-text.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.