cartesia 0.0.5rc1__tar.gz → 0.1.0__tar.gz

{cartesia-0.0.5rc1 → cartesia-0.1.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: cartesia
-Version: 0.0.5rc1
+Version: 0.1.0
 Summary: The official Python library for the Cartesia API.
 Home-page: 
 Author: Cartesia, Inc.
@@ -10,31 +10,8 @@ Classifier: Programming Language :: Python :: 3
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Requires-Python: >=3.8.0
 Description-Content-Type: text/markdown
-Requires-Dist: aiohttp
-Requires-Dist: httpx
-Requires-Dist: pytest-asyncio
-Requires-Dist: requests
-Requires-Dist: websockets
 Provides-Extra: dev
-Requires-Dist: pre-commit; extra == "dev"
-Requires-Dist: docformatter; extra == "dev"
-Requires-Dist: black==24.1.1; extra == "dev"
-Requires-Dist: isort==5.13.2; extra == "dev"
-Requires-Dist: flake8==7.0.0; extra == "dev"
-Requires-Dist: flake8-bugbear==24.2.6; extra == "dev"
-Requires-Dist: pytest>=8.0.2; extra == "dev"
-Requires-Dist: pytest-cov>=4.1.0; extra == "dev"
-Requires-Dist: twine; extra == "dev"
 Provides-Extra: all
-Requires-Dist: pre-commit; extra == "all"
-Requires-Dist: docformatter; extra == "all"
-Requires-Dist: black==24.1.1; extra == "all"
-Requires-Dist: isort==5.13.2; extra == "all"
-Requires-Dist: flake8==7.0.0; extra == "all"
-Requires-Dist: flake8-bugbear==24.2.6; extra == "all"
-Requires-Dist: pytest>=8.0.2; extra == "all"
-Requires-Dist: pytest-cov>=4.1.0; extra == "all"
-Requires-Dist: twine; extra == "all"
 
 
 # Cartesia Python API Library
@@ -60,13 +37,14 @@ client = CartesiaTTS(api_key=os.environ.get("CARTESIA_API_KEY"))
 voices = client.get_voices()
 voice = client.get_voice_embedding(voice_id=voices["Graham"]["id"])
 transcript = "Hello! Welcome to Cartesia"
+model_id = "genial-planet-1346" # (Optional) We'll specify a default if you don't have a specific model in mind
 
 p = pyaudio.PyAudio()
 
 stream = None
 
 # Generate and stream audio
-for output in client.generate(transcript=transcript, voice=voice, stream=True):
+for output in client.generate(transcript=transcript, voice=voice, model_id=model_id, stream=True):
     buffer = output["audio"]
     rate = output["sampling_rate"]
 
@@ -84,26 +62,68 @@ stream.close()
 p.terminate()
 ```
 
-If you are using Jupyter Notebook or JupyterLab, you can use IPython.display.Audio to play the generated audio directly in the notebook. Here's an example:
+You can also use the async client if you want to make asynchronous API calls:
+```python
+from cartesia.tts import AsyncCartesiaTTS
+import asyncio
+import pyaudio
+import os
+
+async def write_stream():
+    client = AsyncCartesiaTTS(api_key=os.environ.get("CARTESIA_API_KEY"))
+    voices = client.get_voices()
+    voice = client.get_voice_embedding(voice_id=voices["Graham"]["id"])
+    transcript = "Hello! Welcome to Cartesia"
+    model_id = "genial-planet-1346" # (Optional) We'll specify a default if you don't have a specific model in mind
+
+    p = pyaudio.PyAudio()
+
+    stream = None
+
+    # Generate and stream audio
+    async for output in await client.generate(transcript=transcript, voice=voice, model_id=model_id, stream=True):
+        buffer = output["audio"]
+        rate = output["sampling_rate"]
+
+        if not stream:
+            stream = p.open(format=pyaudio.paFloat32,
+                            channels=1,
+                            rate=rate,
+                            output=True)
+
+        # Write the audio data to the stream
+        stream.write(buffer)
+
+    stream.stop_stream()
+    stream.close()
+    p.terminate()
+
+asyncio.run(write_stream())
+```
+
+If you are using Jupyter Notebook or JupyterLab, you can use IPython.display.Audio to play the generated audio directly in the notebook.
+Additionally, in these notebook examples we show how to use the client as a context manager (though this is not required).
 
 ```python
-from cartesia.tts import CartesiaTTS
 from IPython.display import Audio
 import io
 import os
+import numpy as np
 
-client = CartesiaTTS(api_key=os.environ.get("CARTESIA_API_KEY"))
-voices = client.get_voices()
-voice = client.get_voice_embedding(voice_id=voices["Graham"]["id"])
-transcript = "Hello! Welcome to Cartesia"
+from cartesia.tts import CartesiaTTS
 
-# Create a BytesIO object to store the audio data
-audio_data = io.BytesIO()
+with CartesiaTTS(api_key=os.environ.get("CARTESIA_API_KEY")) as client:
+    voices = client.get_voices()
+    voice = client.get_voice_embedding(voice_id=voices["Graham"]["id"])
+    transcript = "Hello! Welcome to Cartesia"
 
-# Generate and stream audio
-for output in client.generate(transcript=transcript, voice=voice, stream=True):
-    buffer = output["audio"]
-    audio_data.write(buffer)
+    # Create a BytesIO object to store the audio data
+    audio_data = io.BytesIO()
+
+    # Generate and stream audio
+    for output in client.generate(transcript=transcript, voice=voice, stream=True):
+        buffer = output["audio"]
+        audio_data.write(buffer)
 
 # Set the cursor position to the beginning of the BytesIO object
 audio_data.seek(0)
@@ -115,25 +135,27 @@ audio = Audio(np.frombuffer(audio_data.read(), dtype=np.float32), rate=output["s
 display(audio)
 ```
 
-You can also use the async client if you want to make asynchronous API calls. The usage is very similar:
+Below is the same example using the async client:
 ```python
-from cartesia.tts import AsyncCartesiaTTS
 from IPython.display import Audio
 import io
 import os
+import numpy as np
 
-client = AsyncCartesiaTTS(api_key=os.environ.get("CARTESIA_API_KEY"))
-voices = client.get_voices()
-voice = client.get_voice_embedding(voice_id=voices["Graham"]["id"])
-transcript = "Hello! Welcome to Cartesia"
+from cartesia.tts import AsyncCartesiaTTS
 
-# Create a BytesIO object to store the audio data
-audio_data = io.BytesIO()
+async with AsyncCartesiaTTS(api_key=os.environ.get("CARTESIA_API_KEY")) as client:
+    voices = client.get_voices()
+    voice = client.get_voice_embedding(voice_id=voices["Graham"]["id"])
+    transcript = "Hello! Welcome to Cartesia"
 
-# Generate and stream audio
-async for output in client.generate(transcript=transcript, voice=voice, stream=True):
-    buffer = output["audio"]
-    audio_data.write(buffer)
+    # Create a BytesIO object to store the audio data
+    audio_data = io.BytesIO()
+
+    # Generate and stream audio
+    async for output in await client.generate(transcript=transcript, voice=voice, stream=True):
+        buffer = output["audio"]
+        audio_data.write(buffer)
 
 # Set the cursor position to the beginning of the BytesIO object
 audio_data.seek(0)

{cartesia-0.0.5rc1 → cartesia-0.1.0}/README.md

@@ -21,13 +21,14 @@ client = CartesiaTTS(api_key=os.environ.get("CARTESIA_API_KEY"))
 voices = client.get_voices()
 voice = client.get_voice_embedding(voice_id=voices["Graham"]["id"])
 transcript = "Hello! Welcome to Cartesia"
+model_id = "genial-planet-1346" # (Optional) We'll specify a default if you don't have a specific model in mind
 
 p = pyaudio.PyAudio()
 
 stream = None
 
 # Generate and stream audio
-for output in client.generate(transcript=transcript, voice=voice, stream=True):
+for output in client.generate(transcript=transcript, voice=voice, model_id=model_id, stream=True):
     buffer = output["audio"]
     rate = output["sampling_rate"]
 
@@ -45,26 +46,68 @@ stream.close()
 p.terminate()
 ```
 
-If you are using Jupyter Notebook or JupyterLab, you can use IPython.display.Audio to play the generated audio directly in the notebook. Here's an example:
+You can also use the async client if you want to make asynchronous API calls:
+```python
+from cartesia.tts import AsyncCartesiaTTS
+import asyncio
+import pyaudio
+import os
+
+async def write_stream():
+    client = AsyncCartesiaTTS(api_key=os.environ.get("CARTESIA_API_KEY"))
+    voices = client.get_voices()
+    voice = client.get_voice_embedding(voice_id=voices["Graham"]["id"])
+    transcript = "Hello! Welcome to Cartesia"
+    model_id = "genial-planet-1346" # (Optional) We'll specify a default if you don't have a specific model in mind
+
+    p = pyaudio.PyAudio()
+
+    stream = None
+
+    # Generate and stream audio
+    async for output in await client.generate(transcript=transcript, voice=voice, model_id=model_id, stream=True):
+        buffer = output["audio"]
+        rate = output["sampling_rate"]
+
+        if not stream:
+            stream = p.open(format=pyaudio.paFloat32,
+                            channels=1,
+                            rate=rate,
+                            output=True)
+
+        # Write the audio data to the stream
+        stream.write(buffer)
+
+    stream.stop_stream()
+    stream.close()
+    p.terminate()
+
+asyncio.run(write_stream())
+```
+
+If you are using Jupyter Notebook or JupyterLab, you can use IPython.display.Audio to play the generated audio directly in the notebook.
+Additionally, in these notebook examples we show how to use the client as a context manager (though this is not required).
 
 ```python
-from cartesia.tts import CartesiaTTS
 from IPython.display import Audio
 import io
 import os
+import numpy as np
 
-client = CartesiaTTS(api_key=os.environ.get("CARTESIA_API_KEY"))
-voices = client.get_voices()
-voice = client.get_voice_embedding(voice_id=voices["Graham"]["id"])
-transcript = "Hello! Welcome to Cartesia"
+from cartesia.tts import CartesiaTTS
 
-# Create a BytesIO object to store the audio data
-audio_data = io.BytesIO()
+with CartesiaTTS(api_key=os.environ.get("CARTESIA_API_KEY")) as client:
+    voices = client.get_voices()
+    voice = client.get_voice_embedding(voice_id=voices["Graham"]["id"])
+    transcript = "Hello! Welcome to Cartesia"
 
-# Generate and stream audio
-for output in client.generate(transcript=transcript, voice=voice, stream=True):
-    buffer = output["audio"]
-    audio_data.write(buffer)
+    # Create a BytesIO object to store the audio data
+    audio_data = io.BytesIO()
+
+    # Generate and stream audio
+    for output in client.generate(transcript=transcript, voice=voice, stream=True):
+        buffer = output["audio"]
+        audio_data.write(buffer)
 
 # Set the cursor position to the beginning of the BytesIO object
 audio_data.seek(0)
@@ -76,25 +119,27 @@ audio = Audio(np.frombuffer(audio_data.read(), dtype=np.float32), rate=output["s
 display(audio)
 ```
 
-You can also use the async client if you want to make asynchronous API calls. The usage is very similar:
+Below is the same example using the async client:
 ```python
-from cartesia.tts import AsyncCartesiaTTS
 from IPython.display import Audio
 import io
 import os
+import numpy as np
 
-client = AsyncCartesiaTTS(api_key=os.environ.get("CARTESIA_API_KEY"))
-voices = client.get_voices()
-voice = client.get_voice_embedding(voice_id=voices["Graham"]["id"])
-transcript = "Hello! Welcome to Cartesia"
+from cartesia.tts import AsyncCartesiaTTS
 
-# Create a BytesIO object to store the audio data
-audio_data = io.BytesIO()
+async with AsyncCartesiaTTS(api_key=os.environ.get("CARTESIA_API_KEY")) as client:
+    voices = client.get_voices()
+    voice = client.get_voice_embedding(voice_id=voices["Graham"]["id"])
+    transcript = "Hello! Welcome to Cartesia"
 
-# Generate and stream audio
-async for output in client.generate(transcript=transcript, voice=voice, stream=True):
-    buffer = output["audio"]
-    audio_data.write(buffer)
+    # Create a BytesIO object to store the audio data
+    audio_data = io.BytesIO()
+
+    # Generate and stream audio
+    async for output in await client.generate(transcript=transcript, voice=voice, stream=True):
+        buffer = output["audio"]
+        audio_data.write(buffer)
 
 # Set the cursor position to the beginning of the BytesIO object
 audio_data.seek(0)

cartesia-0.1.0/cartesia/__init__.py

@@ -0,0 +1,3 @@
+from cartesia.tts import AsyncCartesiaTTS, CartesiaTTS
+
+__all__ = ["CartesiaTTS", "AsyncCartesiaTTS"]

cartesia-0.1.0/cartesia/_types.py

@@ -0,0 +1,42 @@
+from enum import Enum
+from typing import List, Optional, TypedDict, Union
+
+try:
+    import numpy as np
+
+    _NUMPY_AVAILABLE = True
+except ImportError:
+    _NUMPY_AVAILABLE = False
+
+
+class AudioDataReturnType(Enum):
+    BYTES = "bytes"
+    ARRAY = "array"
+
+
+class AudioOutputFormat(Enum):
+    """Supported output formats for the audio."""
+
+    FP32 = "fp32"  # float32
+    PCM = "pcm"  # 16-bit signed integer PCM
+    FP32_16000 = "fp32_16000"  # float32, 16 kHz
+    FP32_22050 = "fp32_22050"  # float32, 22.05 kHz
+    FP32_44100 = "fp32_44100"  # float32, 44.1 kHz
+    PCM_16000 = "pcm_16000"  # 16-bit signed integer PCM, 16 kHz
+    PCM_22050 = "pcm_22050"  # 16-bit signed integer PCM, 22.05 kHz
+    PCM_44100 = "pcm_44100"  # 16-bit signed integer PCM, 44.1 kHz
+
+
+class AudioOutput(TypedDict):
+    audio: Union[bytes, "np.ndarray"]
+    sampling_rate: int
+
+
+Embedding = List[float]
+
+
+class VoiceMetadata(TypedDict):
+    id: str
+    name: str
+    description: str
+    embedding: Optional[Embedding]