| Name | deepdub JSON |
| Version |
0.1.15
JSON |
| download |
| home_page | None |
| Summary | A Python client for interacting with the Deepdub API |
| upload_time | 2025-09-05 10:24:06 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | >=3.9 |
| license | MIT |
| keywords |
deepdub
text-to-speech
tts
voice-cloning
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# DeepDub
A Python client for interacting with the DeepDub API, which provides text-to-speech capabilities with voice cloning features.
## Installation
```bash
pip install deepdub
```
## Features
- Interact with DeepDub's text-to-speech (TTS) API
- Add and manage voice profiles
- Generate speech from text with specified voices
- Command-line interface for easy usage
## Requirements
- Python 3.11+
- API key from DeepDub
## Usage
### Python API Reference
#### Initialization
```python
from deepdub import DeepdubClient
# Initialize with API key directly
client = DeepdubClient(api_key="your-api-key")
# Or use environment variable
# export DEEPDUB_API_KEY=your-api-key
client = DeepdubClient()
```
#### List Voices
```python
# Get all available voices
voices = client.list_voices()
```
Returns a list of voice dictionaries.
#### Add Voice
```python
# Add a new voice from audio file
response = client.add_voice(
data=Path("path/to/audio.mp3"), # Path object, bytes, or base64 string
name="Voice Name",
gender="male", # "male" or "female"
locale="en-US",
publish=False, # Default: False
speaking_style="Neutral", # Default: "Neutral"
age=0 # Default: 0
)
```
Returns the server response with voice information.
#### Text-to-Speech
```python
# Generate speech from text
audio_data = client.tts(
text="Text to be converted to speech",
voice_prompt_id="your-voice-id",
model="dd-etts-2.5", # Default: "dd-etts-2.5"
locale="en-US" # Default: "en-US"
)
# Save the audio data
with open("output.mp3", "wb") as f:
f.write(audio_data)
```
Returns binary audio data.
#### Retroactive Text-to-Speech
```python
# Get URL for generated audio
response = client.tts_retro(
text="Text to be converted to speech",
voice_prompt_id="your-voice-id",
model="dd-etts-2.5", # Default: "dd-etts-2.5"
locale="en-US" # Default: "en-US"
)
# Access the URL
audio_url = response["url"]
```
Returns a dictionary containing the URL to the generated audio.
### Command Line Interface
```bash
# List available voices
deepdub list-voices
# Add a new voice
deepdub add-voice --file path/to/audio.mp3 --name "Voice Name" --gender male --locale en-US
# Generate text-to-speech
deepdub tts --text "Hello, world!" --voice-prompt-id your-voice-id
```
### Python API
```python
from deepdub import DeepdubClient
# Initialize with your API key (or set DEEPDUB_API_KEY environment variable)
client = DeepdubClient(api_key="your-api-key")
# List available voices
voices = client.list_voices()
print(voices)
# Generate speech from text
response = client.tts(
text="Hello, this is a test",
voice_prompt_id="your-voice-id",
locale="en-US"
)
# Save the audio output
with open("output.mp3", "wb") as f:
f.write(response)
```
## Authentication
Set your API key either:
- As an environment variable: `DEEPDUB_API_KEY=your-key`
- When initializing the client: `DeepdubClient(api_key="your-key")`
- Using the `--api-key` flag with CLI commands
## License
[License information]
Raw data
{
"_id": null,
"home_page": null,
"name": "deepdub",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.9",
"maintainer_email": null,
"keywords": "deepdub, text-to-speech, tts, voice-cloning",
"author": null,
"author_email": "Deepdub <info@deepdub.ai>",
"download_url": "https://files.pythonhosted.org/packages/d8/32/e18bd8e108af3011a2557ccf1f525826260450d168bb0604e6eae428d864/deepdub-0.1.15.tar.gz",
"platform": null,
"description": "# DeepDub\n\nA Python client for interacting with the DeepDub API, which provides text-to-speech capabilities with voice cloning features.\n\n## Installation\n\n```bash\npip install deepdub\n```\n\n## Features\n\n- Interact with DeepDub's text-to-speech (TTS) API\n- Add and manage voice profiles\n- Generate speech from text with specified voices\n- Command-line interface for easy usage\n\n## Requirements\n\n- Python 3.11+\n- API key from DeepDub\n\n## Usage\n\n### Python API Reference\n\n#### Initialization\n\n```python\nfrom deepdub import DeepdubClient\n\n# Initialize with API key directly\nclient = DeepdubClient(api_key=\"your-api-key\")\n\n# Or use environment variable\n# export DEEPDUB_API_KEY=your-api-key\nclient = DeepdubClient()\n```\n\n#### List Voices\n\n```python\n# Get all available voices\nvoices = client.list_voices()\n```\n\nReturns a list of voice dictionaries.\n\n#### Add Voice\n\n```python\n# Add a new voice from audio file\nresponse = client.add_voice(\n data=Path(\"path/to/audio.mp3\"), # Path object, bytes, or base64 string\n name=\"Voice Name\",\n gender=\"male\", # \"male\" or \"female\"\n locale=\"en-US\",\n publish=False, # Default: False\n speaking_style=\"Neutral\", # Default: \"Neutral\"\n age=0 # Default: 0\n)\n```\n\nReturns the server response with voice information.\n\n#### Text-to-Speech\n\n```python\n# Generate speech from text\naudio_data = client.tts(\n text=\"Text to be converted to speech\",\n voice_prompt_id=\"your-voice-id\",\n model=\"dd-etts-2.5\", # Default: \"dd-etts-2.5\"\n locale=\"en-US\" # Default: \"en-US\"\n)\n\n# Save the audio data\nwith open(\"output.mp3\", \"wb\") as f:\n f.write(audio_data)\n```\n\nReturns binary audio data.\n\n#### Retroactive Text-to-Speech\n\n```python\n# Get URL for generated audio\nresponse = client.tts_retro(\n text=\"Text to be converted to speech\",\n voice_prompt_id=\"your-voice-id\",\n model=\"dd-etts-2.5\", # Default: \"dd-etts-2.5\"\n locale=\"en-US\" # Default: \"en-US\"\n)\n\n# Access the URL\naudio_url = response[\"url\"]\n```\n\nReturns a dictionary containing the URL to the generated audio.\n\n### Command Line Interface\n\n```bash\n# List available voices\ndeepdub list-voices\n\n# Add a new voice\ndeepdub add-voice --file path/to/audio.mp3 --name \"Voice Name\" --gender male --locale en-US\n\n# Generate text-to-speech\ndeepdub tts --text \"Hello, world!\" --voice-prompt-id your-voice-id\n```\n\n### Python API\n\n```python\nfrom deepdub import DeepdubClient\n\n# Initialize with your API key (or set DEEPDUB_API_KEY environment variable)\nclient = DeepdubClient(api_key=\"your-api-key\")\n\n# List available voices\nvoices = client.list_voices()\nprint(voices)\n\n# Generate speech from text\nresponse = client.tts(\n text=\"Hello, this is a test\",\n voice_prompt_id=\"your-voice-id\",\n locale=\"en-US\"\n)\n\n# Save the audio output\nwith open(\"output.mp3\", \"wb\") as f:\n f.write(response)\n```\n\n## Authentication\n\nSet your API key either:\n- As an environment variable: `DEEPDUB_API_KEY=your-key`\n- When initializing the client: `DeepdubClient(api_key=\"your-key\")`\n- Using the `--api-key` flag with CLI commands\n\n## License\n\n[License information]\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "A Python client for interacting with the Deepdub API",
"version": "0.1.15",
"project_urls": {
"Bug Tracker": "https://github.com/deepdub-ai/deepdub/issues",
"Homepage": "https://github.com/deepdub-ai/deepdub"
},
"split_keywords": [
"deepdub",
" text-to-speech",
" tts",
" voice-cloning"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "9fe37728b3a3e055bda23929935fe6fea2b3fe963c0e0ff40fd311882664a500",
"md5": "3a647b998d3bbd3b3fd47560eb0e9210",
"sha256": "a12eb7a21ab51902973f7f47cb09ea5303707f0c281f8ce18ca0c740dc344ce0"
},
"downloads": -1,
"filename": "deepdub-0.1.15-py3-none-any.whl",
"has_sig": false,
"md5_digest": "3a647b998d3bbd3b3fd47560eb0e9210",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.9",
"size": 8370,
"upload_time": "2025-09-05T10:24:05",
"upload_time_iso_8601": "2025-09-05T10:24:05.408373Z",
"url": "https://files.pythonhosted.org/packages/9f/e3/7728b3a3e055bda23929935fe6fea2b3fe963c0e0ff40fd311882664a500/deepdub-0.1.15-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "d832e18bd8e108af3011a2557ccf1f525826260450d168bb0604e6eae428d864",
"md5": "52dd0629ade48bc3f1addf872f77d751",
"sha256": "fb7160b7d4c55da22e0e8df44f6623b80215f0fa04f131332815f8f19e82bbb4"
},
"downloads": -1,
"filename": "deepdub-0.1.15.tar.gz",
"has_sig": false,
"md5_digest": "52dd0629ade48bc3f1addf872f77d751",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.9",
"size": 8958,
"upload_time": "2025-09-05T10:24:06",
"upload_time_iso_8601": "2025-09-05T10:24:06.610020Z",
"url": "https://files.pythonhosted.org/packages/d8/32/e18bd8e108af3011a2557ccf1f525826260450d168bb0604e6eae428d864/deepdub-0.1.15.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-09-05 10:24:06",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "deepdub-ai",
"github_project": "deepdub",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "deepdub"
}
