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

# Speech to text

You could use Keywords AI's unified LLM API to call Speech-to-text model to turn audio into text.

Keywords AI now supports `whisper-1` from OpenAI.

## Integration steps:

<Steps>
  <Step title="Get your OpenAI API key">
    Go to [OpenAI API plaform](https://platform.openai.com/api-keys) to get your OpenAI API key.
  </Step>

  <Step title="Add OpenAI's API key in Providers">
    You should add your OpenAI's API key on [Keywords AI credentials page](https://platform.keywordsai.co/platform/api/providers).

    <img height="200" width="500" src="https://keywordsai-static.s3.us-east-1.amazonaws.com/docs/settings/providers.jpg" />
  </Step>

  <Step title="Call your speech-to-text model">
    <CodeGroup>
      ```Python OpenAI Python theme={"system"}
      from openai import OpenAI

      client = OpenAI(
          base_url="https://api.keywordsai.co/api/",
          api_key="YOUR_KEYWORDSAI_API_KEY",
      )

      audio_file= open("/path/to/file/audio.mp3", "rb")

      response = client.audio.transcriptions.create(
          model="whisper-1",
          file=audio_file,
          extra_body={"customer_identifier": "customer_11"}  # All Keywords AI parameters are supported
      )
      ```

      ```TypeScript OpenAI TypeScript theme={"system"}
      import OpenAI from "openai";
      import fs from "fs";

      const openai = new OpenAI({
        baseURL: "https://api.keywordsai.co/api/",
        apiKey: "YOUR_KEYWORDSAI_API_KEY",
      });

      const transcription = await openai.audio.transcriptions.create({
        model: "whisper-1",
        file: fs.createReadStream("/path/to/file/audio.mp3"),
        extra_body: { customer_identifier: "customer_11" } // All Keywords AI parameters are supported
      });

      ```

      ```python Python theme={"system"}
      import requests
      def demo_call(input, 
                    model="whisper-1",
                    token="YOUR_KEYWORDS_AI_API_KEY",
                    ):
          headers = {
              'Content-Type': 'application/json',
              'Authorization': f'Bearer {token}',
          }

          data = {
              'model': model,
              'file': input,
              'customer_identifier': "customer_11"
          }

          response = requests.post('https://api.keywordsai.co/api/audio/transcription', headers=headers, json=data)
          return response

      audio_file= open("/path/to/file/audio.mp3", "rb")
      print(demo_call(audio_file).json())
      ```

      ```TypeScript TypeScript theme={"system"}
      // Define the function with TypeScript
      fetch('https://api.keywordsai.co/api/audio/transcription', {
        method: 'POST',
        headers: {
          'Content-Type': 'application/json',
          'Authorization': 'Bearer YOUR_KEYWORDS_AI_API_KEY'
        },
          body: JSON.stringify({
              model: 'whisper-1',
              file: fs.createReadStream("/path/to/file/audio.mp3"),
              customer_identifier: "customer_11"
          })
      })
      .then(response => response.json())
      .then(data => console.log(data));
      ```
    </CodeGroup>
  </Step>
</Steps>

## OpenAI parameters

<ParamField path="file" type="file" required>
  The audio file object (not file name) translate, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.
</ParamField>

<ParamField path="model" type="string" required>
  ID of the model to use. Only `whisper-1` is currently available.
</ParamField>

<ParamField path="language" type="string">
  The language of the input audio. Supplying the input language in [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) format will improve accuracy and latency.
</ParamField>

<ParamField path="prompt" type="string">
  An optional text to guide the model's style or continue a previous audio segment. The [prompt](https://platform.openai.com/docs/guides/speech-to-text/prompting) should match the audio language.
</ParamField>

<ParamField path="response_format" type="string" default={"json"}>
  The format of the transcript output, in one of these options: `json`, `text`, `srt`, `verbose_json`, or `vtt`.
</ParamField>

<ParamField path="temperature" type="number" default={0}>
  The format of the transcript output, in one of these options: `json`, `text`, `srt`, `verbose_json`, or `vtt`.
</ParamField>

<ParamField path="timestamp_granularities" type="array" default={"segment"}>
  The timestamp granularities to populate for this transcription. response\_format must be set verbose\_json to use timestamp granularities. Either or both of these options are supported: `word`, or `segment`. Note: There is no additional latency for segment timestamps, but generating word timestamps incurs additional latency.
</ParamField>

## Keywords AI parameters

See how to make a standard Keywords AI API call in the [Quick Start](/get-started/quickstart/gateway) guide.

### Generation parameters

<ParamField path="customer_credentials" type="object">
  You can pass in your customer's credentials for [supported providers](/integration/overview) and use their credits when our proxy is calling models from those providers. <br />See details [here](/documentation/admin/llm_provider_keys)

  <Accordion title="Example">
    ```json theme={"system"}
    "customer_credentials": {

      "openai": {
        "api_key": "YOUR_OPENAI_API_KEY",
      }
    }
    ```
  </Accordion>
</ParamField>

<ParamField path="disable_log" type="boolean" deafault={false}>
  When set to true, only the request and [performance
  metrics](/documentation/products/dashboard/quickstart) will be recorded, input
  and output messages will be omitted from the log.
</ParamField>

### Observability parameters

<ParamField path="metadata" type="dict">
  You can add any key-value pair to this metadata field for your reference. Check the [details of metadata here.](/documentation/products/logs/configuration/custom_properties)

  Contact [team@keywordsai.co](mailto:team@keywordsai.co) if you need extra parameter support for your use case.

  <Accordion title="Example">
    ```json theme={"system"}
    {
      "my_value_key": "my_value"
    }
    ```
  </Accordion>
</ParamField>

<ParamField path="customer_identifier" type="string">
  Use this as a tag to identify the user associated with the API call. See the [details of customer identifier here.](/documentation/products/users/customer-identifier)

  <Accordion title="Example">
    ```json theme={"system"}
    {
        //...other_params,
        "customer_identifier": "user_123"
    }
    ```
  </Accordion>
</ParamField>

<ParamField path="customer_email" type="string">
  This is the email address of the user associated with the API call. You can add your corresponding user's email address to the request.

  You could also edit customer's emails on the platform. Check the [details of user editing here.](/api-endpoints/observe/users/user-creation-endpoint)

  <Accordion title="Example">
    ```json theme={"system"}
    {
        //...other_params,
        "customer_email": "hendrix@keywordsai.co"
    }
    ```
  </Accordion>
</ParamField>

<ParamField path="thread_identifier" type="string">
  See logs as a conversation log thread. Pass all logs with the same `thread_identifier` to see them in the same thread.

  <Accordion title="Example">
    ```json theme={"system"}
    {
        //...other_params,
        "thread_identifier": "test_thread"
    }
    ```
  </Accordion>
</ParamField>

<ParamField path="request_breakdown" type="boolean" default={false}>
  Adding this returns the summarization of the response in the response body. If streaming is on, the metrics will be streamed as the last chunk.

  <Accordion title="Properties">
    <CodeGroup>
      ```json Regular Response theme={"system"}
      {
        "id": "chatcmpl-7476cf3f-fcc9-4902-a548-a12489856d8a",
        //... main part of the response body ...
        "request_breakdown": {
          "prompt_tokens": 6,
          "completion_tokens": 9,
          "cost": 4.8e-5,
          "prompt_messages": [
            {
              "role": "user",
              "content": "How are you doing today?"
            }
          ],
          "completion_message": {
            "content": " I'm doing well, thanks for asking!",
            "role": "assistant"
          },
          "model": "claude-2",
          "cached": false,
          "timestamp": "2024-02-20T01:23:39.329729Z",
          "status_code": 200,
          "stream": false,
          "latency": 1.8415491580963135,
          "scores": {},
          "category": "Questions",
          "metadata": {},
          "routing_time": 0.18612787732854486,
          "full_request": {
            "messages": [
              {
                "role": "user",
                "content": "How are you doing today?"
              }
            ],
            "model": "claude-2",
            "logprobs": true
          },
          "sentiment_score": 0
        }
      }
      ```

      ```json Streaming Response theme={"system"}
      //... other chunks ...
      // The following is the last chunk
      {
        "id": "request_breakdown",
        "choices": [
          {
            "delta": { "content": null, "role": "assistant" },
            "finish_reason": "stop",
            "request_breakdown": {
              "prompt_tokens": 6,
              "completion_tokens": 9,
              "cost": 4.8e-5, //  In usd
              "prompt_messages": [
                {
                  "role": "user",
                  "content": "How are you doing today?"
                }
              ],
              "completion_message": {
                "content": " I'm doing well, thanks for asking!",
                "role": "assistant"
              },
              "model": "claude-2",
              "cached": false,
              "timestamp": "2024-02-20T01:23:39.329729Z",
              "status_code": 200,
              "stream": false,
              "latency": 1.8415491580963135, // in seconds
              "scores": {},
              "category": "Questions",
              "metadata": {},
              "routing_time": 0.18612787732854486, // in seconds
              "full_request": {
                "messages": [
                  {
                    "role": "user",
                    "content": "How are you doing today?"
                  }
                ],
                "model": "claude-2",
                "logprobs": true
              },
              "sentiment_score": 0
            },
            "index": 0,
            "message": { "content": null, "role": "assistant" }
          }
        ],
        "created": 1706100589,
        "model": "extra_parameter",
        "object": "chat.completion.chunk",
        "system_fingerprint": null,
        "usage": {}
      }
      ```
    </CodeGroup>
  </Accordion>
</ParamField>

<RequestExample />