@inductiv/node-red-openai-api/src/audio/help.html

Enhance your Node-RED projects with advanced AI capabilities.

<section>
    <details>
        <summary style="font-weight: bold;">🔉 Audio</summary>
        <a href="https://developers.openai.com/api/reference/typescript/resources/audio/" target="_blank">Official Documentation
            <i class="fa fa-external-link fa-sm" aria-hidden="true"></i></a>
        <h4 style="font-weight: bolder;"> ⋙ Create Speech</h4>
        <p>Generates audio from the input text.</p>
        <dl class="message-properties">
            <h4>msg.payload Properties</h4>

            <dt>
                input
                <span class="property-type">string</span>
            </dt>
            <dd>The text to generate audio for.</dd>

            <dt>
                model
                <span class="property-type">string</span>
            </dt>
            <dd>One of the available TTS models: <code>tts-1</code>, <code>tts-1-hd</code> or
                <code>gpt-4o-mini-tts</code>.</dd>

            <dt>
                voice
                <span class="property-type">string or object</span>
            </dt>
            <dd>
                The voice to use when generating the audio. You can send a built-in voice name such as
                <code>alloy</code>, <code>ash</code>, <code>ballad</code>, <code>coral</code>, <code>echo</code>,
                <code>fable</code>, <code>onyx</code>, <code>nova</code>, <code>sage</code>, <code>shimmer</code>,
                <code>verse</code>, <code>marin</code>, or <code>cedar</code>. You can also send a custom voice object
                with an id, for example <code>{ "id": "voice_1234" }</code>.
            </dd>

            <dt class="optional">
                instructions
                <span class="property-type">string</span>
            </dt>
            <dd>
                Control the voice of your generated audio with additional instructions. Does not work with
                <code>tts-1</code> or <code>tts-1-hd</code>.
            </dd>

            <dt class="optional">
                response_format
                <span class="property-type">string</span>
            </dt>
            <dd>
                The format to audio in. Supported formats are mp3, opus, aac, flac, wav, and pcm.
            </dd>

            <dt class="optional">
                speed
                <span class="property-type">number</span>
            </dt>
            <dd>
                The speed of the generated audio. Select a value from 0.25 to 4.0. 1.0
                is the default.
            </dd>
        </dl>

        <h4 style="font-weight: bolder;"> ⋙ Create Transcription</h4>
        <p>Transcribes audio into the input language.</p>
        <dl class="message-properties">
            <h4>msg.payload Properties</h4>

            <dt>
                file
                <span class="property-type">file</span>
            </dt>
            <dd>
                Absolute path to the file that's being transcribed, in one of these formats: flac, mp3, mp4, mpeg, mpga,
                m4a, ogg, wav, or webm.
            </dd>
            <dt>
                model
                <span class="property-type">string</span>
            </dt>
            <dd>ID of the model to use.</dd>
            <dt class="optional">
                language
                <span class="property-type">string</span>
            </dt>
            <dd>The language of the input audio.</dd>
            <dt class="optional">
                prompt
                <span class="property-type">string</span>
            </dt>
            <dd>
                An optional text to guide the model's style or continue a previous audio
                segment.
            </dd>
            <dt class="optional">
                response_format
                <span class="property-type">string</span>
            </dt>
            <dd>
                The format of the transcript output, in one of these options: json,
                text, srt, verbose_json, or vtt.
            </dd>
            <dt class="optional">
                temperature
                <span class="property-type">number</span>
            </dt>
            <dd>The sampling temperature, between 0 and 1.</dd>

            <dt class="optional">
                timestamp_granularities
                <span class="property-type">array</span>
            </dt>
            <dd>The timestamp granularities to populate for this transcription. <code>response_format</code> must be set
                to <code>verbose_json</code> to use timestamp granularities. Either or both of these options are
                supported: <code>word</code>, or <code>segment</code>.</dd>
        </dl>

        <h4 style="font-weight: bolder;"> ⋙ Create Translation</h4>
        <p>Translates audio into English.</p>
        <dl class="message-properties">
            <h4>msg.payload Properties</h4>

            <dt>
                file
                <span class="property-type">file</span>
            </dt>
            <dd>
                Absolute path to the file that's being translated, in one of these formats: flac, mp3, mp4, mpeg, mpga,
                m4a, ogg, wav, or webm.
            </dd>
            <dt>
                model
                <span class="property-type"></span>
            </dt>
            <dd>ID of the model to use.</dd>
            <dt class="optional">
                prompt
                <span class="property-type">string</span>
            </dt>
            <dd>
                An optional text to guide the model's style or continue a previous audio
                segment.
            </dd>
            <dt class="optional">
                response_format
                <span class="property-type">string</span>
            </dt>
            <dd>
                The format of the transcript output, in one of these options: json,
                text, srt, verbose_json, or vtt.
            </dd>
            <dt class="optional">
                temperature
                <span class="property-type">number</span>
            </dt>
            <dd>The sampling temperature, between 0 and 1.</dd>
        </dl>

    </details>
</section>