> ## Documentation Index
> Fetch the complete documentation index at: https://assemblyai.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Segment A Phone Call using LLM Gateway

In this guide we will show you how to use AssemblyAI's LLM Gateway to segment a phone call. LLM Gateway provides access to multiple LLM providers through a unified API.

## Quickstart

<Tabs groupId="language">
  <Tab language="python" title="Python" default>
    ```python expandable theme={null}
    import requests
    import time

    base_url = "https://api.assemblyai.com"

    headers = {
        "authorization": "<YOUR_API_KEY>"
    }

    # Step 1: Transcribe and get VTT subtitles
    with open("./my-audio.mp3", "rb") as f:
        response = requests.post(base_url + "/v2/upload", headers=headers, data=f)

    upload_url = response.json()["upload_url"]
    data = {"audio_url": upload_url, "speech_models": ["universal-3-pro"]}

    response = requests.post(base_url + "/v2/transcript", json=data, headers=headers)
    transcript_id = response.json()['id']
    polling_endpoint = base_url + "/v2/transcript/" + transcript_id

    while True:
        transcription_result = requests.get(polling_endpoint, headers=headers).json()
        if transcription_result['status'] == 'completed':
            break
        elif transcription_result['status'] == 'error':
            raise RuntimeError(f"Transcription failed: {transcription_result['error']}")
        else:
            time.sleep(3)

    # Get VTT subtitles
    vtt_response = requests.get(f"{polling_endpoint}/vtt", headers=headers)
    vtt_content = vtt_response.text

    # Step 2: Define phases and analyze with LLM Gateway
    phases = ["Introduction", "Complaint", "Resolution", "Goodbye"]

    prompt = f'''
    Analyze the following transcript of a phone call conversation and divide it into the following phases:
    {', '.join(phases)}

    You will be given the transcript in the format of VTT captions.

    For each phase:
    1. Identify the start and end timestamps (in seconds)
    2. Provide a brief summary of what happened in that phase

    Format your response as a JSON object with the following structure:
    {{
        "phases": [
            {{
                "name": "Phase Name",
                "start_time": start_time_in_seconds,
                "end_time": end_time_in_seconds,
                "summary": "Brief summary of the phase"
            }},
            ...
        ]
    }}

    Ensure that all parts of the conversation are covered by a phase, using "Other" for any parts that don't fit into the specified phases.
    '''

    llm_gateway_data = {
        "model": "claude-sonnet-4-5-20250929",
        "messages": [
            {"role": "user", "content": f"{prompt}\n\nVTT Transcript:\n{vtt_content}"}
        ],
        "max_tokens": 2000
    }

    response = requests.post(
        "https://llm-gateway.assemblyai.com/v1/chat/completions",
        headers=headers,
        json=llm_gateway_data
    )

    result = response.json()["choices"][0]["message"]["content"]
    print(result)
    ```
  </Tab>

  <Tab language="javascript" title="JavaScript">
    ```javascript expandable theme={null}
    import fs from "fs-extra";

    const baseUrl = "https://api.assemblyai.com";

    const headers = {
      authorization: "<YOUR_API_KEY>",
    };

    // Step 1: Transcribe and get VTT subtitles
    const audioData = await fs.readFile("./my-audio.mp3");
    let res = await fetch(`${baseUrl}/v2/upload`, {
      method: "POST",
      headers,
      body: audioData,
    });
    if (!res.ok) throw new Error(`Error: ${res.status}`);
    const uploadResponse = await res.json();
    const uploadUrl = uploadResponse.upload_url;

    const data = { audio_url: uploadUrl, speech_models: ["universal-3-pro"] };

    res = await fetch(`${baseUrl}/v2/transcript`, {
      method: "POST",
      headers: { ...headers, "Content-Type": "application/json" },
      body: JSON.stringify(data),
    });
    if (!res.ok) throw new Error(`Error: ${res.status}`);
    const transcriptResponse = await res.json();
    const transcriptId = transcriptResponse.id;
    const pollingEndpoint = `${baseUrl}/v2/transcript/${transcriptId}`;

    while (true) {
      res = await fetch(pollingEndpoint, { headers });
      if (!res.ok) throw new Error(`Error: ${res.status}`);
      const transcriptionResult = await res.json();
      if (transcriptionResult.status === "completed") {
        break;
      } else if (transcriptionResult.status === "error") {
        throw new Error(`Transcription failed: ${transcriptionResult.error}`);
      } else {
        await new Promise((resolve) => setTimeout(resolve, 3000));
      }
    }

    // Get VTT subtitles
    res = await fetch(`${pollingEndpoint}/vtt`, { headers });
    if (!res.ok) throw new Error(`Error: ${res.status}`);
    const vttContent = await res.text();

    // Step 2: Define phases and analyze with LLM Gateway
    const phases = ["Introduction", "Complaint", "Resolution", "Goodbye"];

    const prompt = `
    Analyze the following transcript of a phone call conversation and divide it into the following phases:
    ${phases.join(", ")}

    You will be given the transcript in the format of VTT captions.

    For each phase:
    1. Identify the start and end timestamps (in seconds)
    2. Provide a brief summary of what happened in that phase

    Format your response as a JSON object with the following structure:
    {
        "phases": [
            {
                "name": "Phase Name",
                "start_time": start_time_in_seconds,
                "end_time": end_time_in_seconds,
                "summary": "Brief summary of the phase"
            },
            ...
        ]
    }

    Ensure that all parts of the conversation are covered by a phase, using "Other" for any parts that don't fit into the specified phases.
    `;

    const llmGatewayData = {
      model: "claude-sonnet-4-5-20250929",
      messages: [
        { role: "user", content: `${prompt}\n\nVTT Transcript:\n${vttContent}` },
      ],
      max_tokens: 2000,
    };

    res = await fetch("https://llm-gateway.assemblyai.com/v1/chat/completions", {
      method: "POST",
      headers: { ...headers, "Content-Type": "application/json" },
      body: JSON.stringify(llmGatewayData),
    });
    if (!res.ok) throw new Error(`Error: ${res.status}`);
    const response = await res.json();

    const result = response.choices[0].message.content;
    console.log(result);
    ```
  </Tab>
</Tabs>

## Get Started

Before we begin, make sure you have an AssemblyAI account and an API key. You can [sign up for an AssemblyAI account](https://www.assemblyai.com/dashboard/home) and get your API key from your dashboard.

## Step-by-Step Instructions

Install the required packages:

<Tabs groupId="language">
  <Tab language="python" title="Python" default>
    ```bash theme={null}
    pip install requests
    ```
  </Tab>

  <Tab language="javascript" title="JavaScript">
    ```bash theme={null}
    npm install fs-extra
    ```
  </Tab>
</Tabs>

Set up your API client and transcribe the audio file:

<Tabs groupId="language">
  <Tab language="python" title="Python" default>
    ```python expandable theme={null}
    import requests
    import time

    base_url = "https://api.assemblyai.com"

    headers = {
        "authorization": "<YOUR_API_KEY>"
    }

    with open("./my-audio.mp3", "rb") as f:
        response = requests.post(base_url + "/v2/upload",
                                headers=headers,
                                data=f)

    upload_url = response.json()["upload_url"]

    data = {
        "audio_url": upload_url, # You can also use a URL to an audio or video file on the web
        "speech_models": ["universal-3-pro"]
    }

    url = base_url + "/v2/transcript"
    response = requests.post(url, json=data, headers=headers)

    transcript_id = response.json()['id']
    polling_endpoint = base_url + "/v2/transcript/" + transcript_id

    while True:
        transcription_result = requests.get(polling_endpoint, headers=headers).json()

        if transcription_result['status'] == 'completed':
            print(f"Transcript ID: {transcript_id}")
            break

        elif transcription_result['status'] == 'error':
            raise RuntimeError(f"Transcription failed: {transcription_result['error']}")

        else:
            time.sleep(3)

    # Get VTT subtitles for timestamp information
    vtt_response = requests.get(f"{polling_endpoint}/vtt", headers=headers)
    vtt_content = vtt_response.text

    with open(f"transcript_{transcript_id}.vtt", "w") as vtt_file:
        vtt_file.write(vtt_content)
    ```
  </Tab>

  <Tab language="javascript" title="JavaScript">
    ```javascript expandable theme={null}
    import fs from "fs-extra";

    const baseUrl = "https://api.assemblyai.com";

    const headers = {
      authorization: "<YOUR_API_KEY>",
    };

    const audioData = await fs.readFile("./my-audio.mp3");
    let res = await fetch(`${baseUrl}/v2/upload`, {
      method: "POST",
      headers,
      body: audioData,
    });
    if (!res.ok) throw new Error(`Error: ${res.status}`);
    const uploadResponse = await res.json();
    const uploadUrl = uploadResponse.upload_url;

    const data = {
      audio_url: uploadUrl, // You can also use a URL to an audio or video file on the web
      speech_models: ["universal-3-pro"],
    };

    const url = `${baseUrl}/v2/transcript`;
    res = await fetch(url, {
      method: "POST",
      headers: { ...headers, "Content-Type": "application/json" },
      body: JSON.stringify(data),
    });
    if (!res.ok) throw new Error(`Error: ${res.status}`);
    const transcriptResponse = await res.json();

    const transcriptId = transcriptResponse.id;
    const pollingEndpoint = `${baseUrl}/v2/transcript/${transcriptId}`;

    while (true) {
      res = await fetch(pollingEndpoint, { headers });
      if (!res.ok) throw new Error(`Error: ${res.status}`);
      const transcriptionResult = await res.json();

      if (transcriptionResult.status === "completed") {
        console.log("Transcript ID:", transcriptId);
        break;
      } else if (transcriptionResult.status === "error") {
        throw new Error(`Transcription failed: ${transcriptionResult.error}`);
      } else {
        await new Promise((resolve) => setTimeout(resolve, 3000));
      }
    }

    // Get VTT subtitles for timestamp information
    res = await fetch(`${pollingEndpoint}/vtt`, { headers });
    if (!res.ok) throw new Error(`Error: ${res.status}`);
    const vttContent = await res.text();

    fs.writeFileSync(`transcript_${transcriptId}.vtt`, vttContent);
    ```
  </Tab>
</Tabs>

Define the phases you want to identify.

Here is an example of `phases` that can be used for customer support calls:

<Tabs groupId="language">
  <Tab language="python" title="Python" default>
    ```python theme={null}
    phases = [
        "Introduction",
        "Complaint",
        "Resolution",
        "Goodbye"
    ]
    ```
  </Tab>

  <Tab language="javascript" title="JavaScript">
    ```javascript theme={null}
    const phases = [
      "Introduction",
      "Complaint",
      "Resolution",
      "Goodbye",
    ];
    ```
  </Tab>
</Tabs>

Use LLM Gateway to analyze the transcript and divide it into phases. This is an example prompt, which you can modify to suit your specific requirements.

<Tabs groupId="language">
  <Tab language="python" title="Python" default>
    ```python expandable theme={null}
    prompt = f'''
    Analyze the following transcript of a phone call conversation and divide it into the following phases:
    {', '.join(phases)}

    You will be given the transcript in the format of VTT captions.

    For each phase:
    1. Identify the start and end timestamps (in seconds)
    2. Provide a brief summary of what happened in that phase

    Format your response as a JSON object with the following structure:
    {{
        "phases": [
            {{
                "name": "Phase Name",
                "start_time": start_time_in_seconds,
                "end_time": end_time_in_seconds,
                "summary": "Brief summary of the phase"
            }},
            ...
        ]
    }}

    Ensure that all parts of the conversation are covered by a phase, using "Other" for any parts that don't fit into the specified phases.
    '''

    llm_gateway_data = {
        "model": "claude-sonnet-4-5-20250929",
        "messages": [
            {"role": "user", "content": f"{prompt}\n\nVTT Transcript:\n{vtt_content}"}
        ],
        "max_tokens": 2000
    }

    response = requests.post(
        "https://llm-gateway.assemblyai.com/v1/chat/completions",
        headers=headers,
        json=llm_gateway_data
    )

    result = response.json()["choices"][0]["message"]["content"]
    print(result)
    ```
  </Tab>

  <Tab language="javascript" title="JavaScript">
    ```javascript expandable theme={null}
    const prompt = `
    Analyze the following transcript of a phone call conversation and divide it into the following phases:
    ${phases.join(", ")}

    You will be given the transcript in the format of VTT captions.

    For each phase:
    1. Identify the start and end timestamps (in seconds)
    2. Provide a brief summary of what happened in that phase

    Format your response as a JSON object with the following structure:
    {
        "phases": [
            {
                "name": "Phase Name",
                "start_time": start_time_in_seconds,
                "end_time": end_time_in_seconds,
                "summary": "Brief summary of the phase"
            },
            ...
        ]
    }

    Ensure that all parts of the conversation are covered by a phase, using "Other" for any parts that don't fit into the specified phases.
    `;

    const llmGatewayData = {
      model: "claude-sonnet-4-5-20250929",
      messages: [
        { role: "user", content: `${prompt}\n\nVTT Transcript:\n${vttContent}` },
      ],
      max_tokens: 2000,
    };

    let res = await fetch("https://llm-gateway.assemblyai.com/v1/chat/completions", {
      method: "POST",
      headers: { ...headers, "Content-Type": "application/json" },
      body: JSON.stringify(llmGatewayData),
    });
    if (!res.ok) throw new Error(`Error: ${res.status}`);
    const response = await res.json();

    const result = response.choices[0].message.content;
    console.log(result);
    ```
  </Tab>
</Tabs>

Example output of the analysis of a transcript divided into phases and formatted as a JSON object:

```expandable theme={null}

{
    "phases": [
        {
            "name": "Introduction",
            "start_time": 1.52,
            "end_time": 15.57,
            "summary": "The customer service representative greets the caller and asks how they can help. The caller states they want to know the status of their order refund."
        },
        {
            "name": "Complaint",
            "start_time": 15.57,
            "end_time": 59.41,
            "summary": "The representative asks for the order ID, which the caller provides. The representative confirms the order details and that it was cancelled. The caller mentions they couldn't complete their test."
        },
        {
            "name": "Resolution",
            "start_time": 59.41,
            "end_time": 210.01,
            "summary": "The representative informs the caller that the refund was initiated on April 8th and will be credited by April 21st. They explain the refund timeline and bank processing days. The caller expresses some confusion about the timeline, and the representative clarifies the process."
        },
        {
            "name": "Goodbye",
            "start_time": 210.01,
            "end_time": 235.8,
            "summary": "The caller accepts the explanation. The representative asks if there's anything else they can help with, requests feedback, and concludes the call with a farewell."
        }
    ]
}
```