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

2.3 KB
Raw Blame
<a id="camel.models.base_audio_model"></a>

<a id="camel.models.base_audio_model.BaseAudioModel"></a>

## BaseAudioModel

```python
class BaseAudioModel(ABC):
```

Base class for audio models providing Text-to-Speech (TTS) and
Speech-to-Text (STT) functionality.

<a id="camel.models.base_audio_model.BaseAudioModel.__init__"></a>

### __init__

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

Initialize an instance of BaseAudioModel.

**Parameters:**

- **api_key** (Optional[str]): API key for the audio service. If not provided, will look for an environment variable specific to the implementation.
- **url** (Optional[str]): Base URL for the audio API. If not provided, will use a default URL or look for an environment variable specific to the implementation.
- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`)

<a id="camel.models.base_audio_model.BaseAudioModel.text_to_speech"></a>

### text_to_speech

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

Convert text to speech.

**Parameters:**

- **input** (str): The text to be converted to speech.
- **storage_path** (str): The local path to store the generated speech file. **kwargs (Any): Extra kwargs passed to the TTS API.

**Returns:**

  Any: The response from the TTS API, which may vary by
implementation.

<a id="camel.models.base_audio_model.BaseAudioModel.speech_to_text"></a>

### speech_to_text

```python
def speech_to_text(self, audio_file_path: str, **kwargs: Any):
```

Convert speech audio to text.

**Parameters:**

- **audio_file_path** (str): The audio file path to transcribe. **kwargs (Any): Extra keyword arguments passed to the Speech-to-Text (STT) API.

**Returns:**

  str: The transcribed text.

<a id="camel.models.base_audio_model.BaseAudioModel._ensure_directory_exists"></a>

### _ensure_directory_exists

```python
def _ensure_directory_exists(self, file_path: str):
```

Ensure the directory for the given file path exists.

**Parameters:**

- **file_path** (str): The file path for which to ensure the directory exists.