Skip to content

OpenAI Audio 操作#

¥OpenAI Audio operations

使用此操作在 OpenAI 中生成音频，或转录或翻译录音。有关 OpenAI 节点本身的更多信息，请参阅 OpenAI。

¥Use this operation to generate an audio, or transcribe or translate a recording in OpenAI. Refer to OpenAI for more information on the OpenAI node itself.

生成音频#

¥Generate Audio

使用此操作根据文本提示创建音频。

¥Use this operation to create audio from a text prompt.

请输入以下参数：

¥Enter these parameters:

¥Credential to connect with: Create or select an existing OpenAI credential.

  • 资源：选择“音频”。

¥Resource: Select Audio.

  • 操作：选择“生成音频”。

¥Operation: Select Generate Audio.

  • 模型：选择用于生成音频的模型。有关更多信息，请参阅 TTS | OpenAI。

¥Model: Select the model you want to use to generate the audio. Refer to TTS | OpenAI for more information.

  • TTS-1:使用此选项优化速度。

    ¥TTS-1: Use this to optimize for speed.

  • TTS-1-HD:使用此选项优化质量。

    ¥TTS-1-HD: Use this to optimize for quality.

  • 文本输入：输入要生成音频的文本。最大长度为 4096 个字符。

¥Text Input: Enter the text to generate the audio for. The maximum length is 4096 characters.

¥Voice: Select a voice to use when generating the audio. Listen to the previews of the voices in Text to speech guide | OpenAI.

选项#

¥Options

  • 响应格式：选择音频响应的格式。选择 MP3（默认）、OPUS、AAC、FLAC、WAV 和 PCM 格式。

¥Response Format: Select the format for the audio response. Choose from MP3 (default), OPUS, AAC, FLAC, WAV, and PCM.

  • 音频速度：输入生成的音频速度，取值范围为 0.25 到 4.0。默认为 1。

¥Audio Speed: Enter the speed for the generated audio from a value from 0.25 to 4.0. Defaults to 1.

  • 输出字段：默认为 data。输入要存放二进制文件数据的输出字段名称。

¥Put Output in Field: Defaults to data. Enter the name of the output field to put the binary file data in.

有关更多信息，请参阅 创建语音 | OpenAI 文档。

¥Refer to Create speech | OpenAI documentation for more information.

转录录音#

¥Transcribe a Recording

使用此操作将音频转录为文本。OpenAI API 将音频文件大小限制为 25 MB。OpenAI 默认使用 whisper-1 模型。

¥Use this operation to transcribe audio into text. OpenAI API limits the size of the audio file to 25 MB. OpenAI will use the whisper-1 model by default.

请输入以下参数：

¥Enter these parameters:

¥Credential to connect with: Create or select an existing OpenAI credential.

  • 资源：选择“音频”。

¥Resource: Select Audio.

  • 操作：选择“转录录音”。

¥Operation: Select Transcribe a Recording.

  • 输入数据字段名称：默认为 data。请输入包含以下格式之一的音频文件的二进制属性的名称：.flac、.mp3、.mp4、.mpeg、.mpga、.m4a、.ogg、.wav 或 .webm。

¥Input Data Field Name: Defaults to data. Enter the name of the binary property that contains the audio file in one of these formats: .flac, .mp3, .mp4, .mpeg, .mpga, .m4a, .ogg, .wav, or .webm.

选项#

¥Options

  • 音频文件语言：输入 ISO-639-1 中输入音频的语言。使用此选项可提高准确率并降低延迟。

¥Language of the Audio File: Enter the language of the input audio in ISO-639-1. Use this option to improve accuracy and latency.

  • 输出随机性（温度）：默认为 1.0。调整响应的随机性。取值范围为 0.0（确定性）到 1.0（最大随机性）。我们建议修改此项或输出随机性（Top P），但不要同时修改两者。从中等温度（大约 0.7）开始，并根据观察到的输出进行调整。如果响应过于重复或僵硬，则提高温度。如果他们的工作流过于混乱或偏离轨道，请降低其优先级。

¥Output Randomness (Temperature): Defaults to 1.0. Adjust the randomness of the response. The range is between 0.0 (deterministic) and 1.0 (maximum randomness). We recommend altering this or Output Randomness (Top P) but not both. Start with a medium temperature (around 0.7) and adjust based on the outputs you observe. If the responses are too repetitive or rigid, increase the temperature. If they’re too chaotic or off-track, decrease it.

有关更多信息，请参阅 创建转录 | OpenAI 文档。

¥Refer to Create transcription | OpenAI documentation for more information.

翻译录音#

¥Translate a Recording

使用此操作将音频翻译成英语。OpenAI API 将音频文件大小限制为 25 MB。OpenAI 默认使用 whisper-1 模型。

¥Use this operation to translate audio into English. OpenAI API limits the size of the audio file to 25 MB. OpenAI will use the whisper-1 model by default.

请输入以下参数：

¥Enter these parameters:

¥Credential to connect with: Create or select an existing OpenAI credential.

  • 资源：选择“音频”。

¥Resource: Select Audio.

  • 操作：选择“翻译录音”。

¥Operation: Select Translate a Recording.

  • 输入数据字段名称：默认为 data。请输入包含以下格式之一的音频文件的二进制属性的名称：.flac、.mp3、.mp4、.mpeg、.mpga、.m4a、.ogg、.wav 或 .webm。

¥Input Data Field Name: Defaults to data. Enter the name of the binary property that contains the audio file in one of these formats: .flac, .mp3, .mp4, .mpeg, .mpga, .m4a, .ogg, .wav, or .webm.

选项#

¥Options

  • 输出随机性（温度）：默认为 1.0。调整响应的随机性。取值范围为 0.0（确定性）到 1.0（最大随机性）。我们建议修改此项或输出随机性（Top P），但不要同时修改两者。从中等温度（大约 0.7）开始，并根据观察到的输出进行调整。如果响应过于重复或僵硬，则提高温度。如果他们的工作流过于混乱或偏离轨道，请降低其优先级。

¥Output Randomness (Temperature): Defaults to 1.0. Adjust the randomness of the response. The range is between 0.0 (deterministic) and 1.0 (maximum randomness). We recommend altering this or Output Randomness (Top P) but not both. Start with a medium temperature (around 0.7) and adjust based on the outputs you observe. If the responses are too repetitive or rigid, increase the temperature. If they’re too chaotic or off-track, decrease it.

有关更多信息，请参阅 创建转录 | OpenAI 文档。

¥Refer to Create transcription | OpenAI documentation for more information.

常见问题#

¥Common issues

有关常见错误或问题以及建议的解决方法，请参阅 常见问题。

¥For common errors or issues and suggested resolution steps, refer to Common Issues.