The official Python SDK for interacting with Camb AI's powerful voice and audio generation APIs. Create expressive speech, unique voices, and rich soundscapes with just a few lines of Python.
- Dubbing: Dub your videos into multiple languages with voice cloning!
- Expressive Text-to-Speech: Convert text into natural-sounding speech using a wide range of pre-existing voices.
- Generative Voices: Create entirely new, unique voices from text prompts and descriptions.
- Soundscapes from Text: Generate ambient audio and sound effects from textual descriptions.
- Access to voice cloning, translation, and more (refer to full API documentation).
Install the SDK using pip, ensure Python 3.9+:
pip install camb-sdkOr through
pip install git+https://github.com/Camb-ai/cambai-python-sdkTo use the Camb AI SDK, you'll need an API key. You can authenticate in either of the following ways:
from cambai import CambAI
client = CambAI(api_key="YOUR_CAMB_API_KEY")Set your API key as an environment variable named CAMB_API_KEY:
export CAMB_API_KEY="your_actual_api_key_here"Convert text into spoken audio using one of Camb AI's high-quality voices.
This is useful if you want to play the audio in a web application or share a link.
from cambai import CambAI
from cambai.rest import ApiException
# Initialize client (ensure API key is set)
client = CambAI(api_key="YOUR_CAMB_API_KEY")
try:
print("Generating speech and getting audio URL...")
audio_url = client.text_to_speech(
text="Hello from Camb AI! This is a test of our Text-to-Speech API.",
voice_id=20303 # Example voice ID, find more with client.list_voices()
)
print(f"Success! Your audio is ready at: {audio_url}")
except ApiException as e:
print(f"API Exception when calling text_to_speech: {e}\n")Generate speech and save it as an MP3 file (or other supported formats).
from cambai import CambAI
from cambai.models.output_type import OutputType
from cambai.rest import ApiException
# Initialize client
client = CambAI(api_key="YOUR_CAMB_API_KEY")
file_path = "my_generated_speech.mp3"
try:
print(f"Generating speech and saving to {file_path}...")
client.text_to_speech(
text="This is another test, saving directly to a file.",
voice_id=20303, # Example voice ID
output_type=OutputType.RAW_BYTES, # Specify raw bytes for direct saving
save_to_file=file_path,
verbose=True # For more detailed logging from the SDK
)
print(f"Success! Audio saved to {file_path}")
except ApiException as e:
8000
print(f"API Exception when calling text_to_speech (save to file): {e}\n")You can list available voices to find a voice_id that suits your needs:
try:
voices = client.list_voices()
print(f"Found {len(voices)} voices:")
for voice in voices[:5]: # Print first 5 as an example
print(f" - ID: {voice.id}, Name: {voice.voice_name}, Gender: {voice.gender}, Language: {voice.language}")
except ApiException as e:
print(f"Could not list voices: {e}")Create completely new and unique voices from a textual description of the desired voice characteristics.
from cambai import CambAI
from cambai.rest import ApiException
# Initialize client
client = CambAI(api_key="YOUR_CAMB_API_KEY")
output_file = "generated_voice_output.mp3"
try:
print("Generating a new voice and speech...")
# The 'text_to_voice' method returns a dict consisting of 3 sample URLs
result = client.text_to_voice(
text="Crafting a unique voice with a hint of mystery and warmth.",
voice_description="A smooth, baritone voice with a slight echo, perfect for storytelling.",
verbose=True
)
print(result)
except ApiException as e:
print(f"API Exception when calling text_to_voice: {e}\n")Generate sound effects or ambient audio from a descriptive prompt.
from cambai import CambAI
from cambai.rest import ApiException
# Initialize client
client = CambAI(api_key="YOUR_CAMB_API_KEY")
output_file = "generated_sound_effect.mp3"
try:
print(f"Generating sound effect and saving to {output_file}...")
client.text_to_audio(
prompt="A gentle breeze rustling through autumn leaves in a quiet forest.",
duration=10,
save_to_file=output_file,
verbose=True
)
print(f"Success! Sound effect saved to {output_file}")
except ApiException as e:
print(f"API Exception when calling text_to_audio: {e}\n")Dub videos into different languages with voice cloning and translation capabilities.
from cambai import CambAI
from cambai.rest import ApiException
# Initialize client
client = CambAI(api_key="YOUR_CAMB_API_KEY")
# Call all target languages
print("Listing target languages...")
target_languages = clinet.get_target_languages()
print(f"Found {len(target_languages)} target languages:")
for language in target_languages:
print(f" - {language}")
try:
print("Starting end-to-end dubbing process...")
result = client.end_to_end_dubbing(
video_url="your_accesible_video_url",
source_language=cambai.Languages.NUMBER_1, # English
target_languages=[cambai.Languages.NUMBER_81], # Add more target languages as needed
verbose=True
)
print("Dubbing completed successfully!")
# The result contains output_video_url, output_audio_url, and transcript information with timing and speaker details
print(f"Result: {result}")
except ApiException as e:
print(f"API Exception when calling end_to_end_dubbing: {e}\n")The Camb AI SDK offers a wide range of capabilities beyond these examples, including:
- Voice Cloning
- Translated TTS
- Audio Dubbing
- Transcription
- And more!
Please refer to the Official Camb AI API Documentation for a comprehensive list of features and advanced usage patterns.
This project is licensed under the MIT License - see the LICENSE file for details.