Skip to content

armgit / camel

Public Imported from GitHub
0

🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org

3.4 KB
Raw Blame
<a id="camel.models.openai_audio_models"></a>

<a id="camel.models.openai_audio_models.OpenAIAudioModels"></a>

## OpenAIAudioModels

```python
class OpenAIAudioModels(BaseAudioModel):
```

Provides access to OpenAI's Text-to-Speech (TTS) and Speech_to_Text
(STT) models.

<a id="camel.models.openai_audio_models.OpenAIAudioModels.__init__"></a>

### __init__

```python
def __init__(
    self,
    api_key: Optional[str] = None,
    url: Optional[str] = None,
    timeout: Optional[float] = None
):
```

Initialize an instance of OpenAI.

<a id="camel.models.openai_audio_models.OpenAIAudioModels.text_to_speech"></a>

### text_to_speech

```python
def text_to_speech(self, input: str, **kwargs: Any):
```

Convert text to speech using OpenAI's TTS model. This method
converts the given input text to speech using the specified model and
voice.

**Parameters:**

- **input** (str): The text to be converted to speech.
- **model_type** (AudioModelType, optional): The TTS model to use. Defaults to `AudioModelType.TTS_1`.
- **voice** (VoiceType, optional): The voice to be used for generating speech. Defaults to `VoiceType.ALLOY`.
- **storage_path** (str, optional): The local path to store the generated speech file if provided, defaults to `None`. **kwargs (Any): Extra kwargs passed to the TTS API.

**Returns:**

  Union[List[_legacy_response.HttpxBinaryResponseContent],
_legacy_response.HttpxBinaryResponseContent]: List of response
content object from OpenAI if input characters more than 4096,
single response content if input characters less than 4096.

<a id="camel.models.openai_audio_models.OpenAIAudioModels._split_audio"></a>

### _split_audio

```python
def _split_audio(self, audio_file_path: str, chunk_size_mb: int = 24):
```

Split the audio file into smaller chunks. Since the Whisper API
only supports files that are less than 25 MB.

**Parameters:**

- **audio_file_path** (str): Path to the input audio file.
- **chunk_size_mb** (int, optional): Size of each chunk in megabytes. Defaults to `24`.

**Returns:**

  list: List of paths to the split audio files.

<a id="camel.models.openai_audio_models.OpenAIAudioModels.speech_to_text"></a>

### speech_to_text

```python
def speech_to_text(
    self,
    audio_file_path: str,
    translate_into_english: bool = False,
    **kwargs: Any
):
```

Convert speech audio to text.

**Parameters:**

- **audio_file_path** (str): The audio file path, supporting one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.
- **translate_into_english** (bool, optional): Whether to translate the speech into English. Defaults to `False`. **kwargs (Any): Extra keyword arguments passed to the Speech-to-Text (STT) API.

**Returns:**

  str: The output text.

<a id="camel.models.openai_audio_models.OpenAIAudioModels.audio_question_answering"></a>

### audio_question_answering

```python
def audio_question_answering(
    self,
    audio_file_path: str,
    question: str,
    model: str = 'gpt-4o-mini-audio-preview',
    **kwargs: Any
):
```

Answer a question directly using the audio content.

**Parameters:**

- **audio_file_path** (str): The path to the audio file.
- **question** (str): The question to ask about the audio content.
- **model** (str, optional): The model to use for audio question answering. (default: :obj:`"gpt-4o-mini-audio-preview"`) **kwargs (Any): Extra keyword arguments passed to the chat completions API.

**Returns:**

  str: The model's response to the question.