cartesia 2.0.0b2__py3-none-any.whl → 2.0.0b8__py3-none-any.whl

cartesia/voices/types/__init__.py

@@ -6,9 +6,12 @@ from .create_voice_request import CreateVoiceRequest
 from .embedding_response import EmbeddingResponse
 from .embedding_specifier import EmbeddingSpecifier
 from .gender import Gender
+from .gender_presentation import GenderPresentation
+from .get_voices_response import GetVoicesResponse
 from .id_specifier import IdSpecifier
 from .localize_dialect import LocalizeDialect
 from .localize_english_dialect import LocalizeEnglishDialect
+from .localize_french_dialect import LocalizeFrenchDialect
 from .localize_portuguese_dialect import LocalizePortugueseDialect
 from .localize_spanish_dialect import LocalizeSpanishDialect
 from .localize_target_language import LocalizeTargetLanguage
@@ -17,6 +20,7 @@ from .mix_voice_specifier import MixVoiceSpecifier
 from .mix_voices_request import MixVoicesRequest
 from .update_voice_request import UpdateVoiceRequest
 from .voice import Voice
+from .voice_expand_options import VoiceExpandOptions
 from .voice_id import VoiceId
 from .voice_metadata import VoiceMetadata
 from .weight import Weight
@@ -28,9 +32,12 @@ __all__ = [
     "EmbeddingResponse",
     "EmbeddingSpecifier",
     "Gender",
+    "GenderPresentation",
+    "GetVoicesResponse",
     "IdSpecifier",
     "LocalizeDialect",
     "LocalizeEnglishDialect",
+    "LocalizeFrenchDialect",
     "LocalizePortugueseDialect",
     "LocalizeSpanishDialect",
     "LocalizeTargetLanguage",
@@ -39,6 +46,7 @@ __all__ = [
     "MixVoicesRequest",
     "UpdateVoiceRequest",
     "Voice",
+    "VoiceExpandOptions",
     "VoiceId",
     "VoiceMetadata",
     "Weight",

cartesia/voices/types/gender_presentation.py

@@ -0,0 +1,5 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+GenderPresentation = typing.Union[typing.Literal["masculine", "feminine", "gender_neutral"], typing.Any]

cartesia/voices/types/get_voices_response.py

@@ -0,0 +1,34 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from ...core.pydantic_utilities import UniversalBaseModel
+import typing
+from .voice import Voice
+import pydantic
+from .voice_id import VoiceId
+from ...core.pydantic_utilities import IS_PYDANTIC_V2
+
+
+class GetVoicesResponse(UniversalBaseModel):
+    data: typing.List[Voice] = pydantic.Field()
+    """
+    The paginated list of Voices.
+    """
+
+    has_more: bool = pydantic.Field()
+    """
+    Whether there are more Voices to fetch (using `starting_after=id`, where id is the ID of the last Voice in the current response).
+    """
+
+    next_page: typing.Optional[VoiceId] = pydantic.Field(default=None)
+    """
+    (Deprecated - use the id of the last Voice in the current response instead.) An ID that can be passed as `starting_after` to get the next page of Voices.
+    """
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

cartesia/voices/types/localize_dialect.py

@@ -4,5 +4,8 @@ import typing
 from .localize_english_dialect import LocalizeEnglishDialect
 from .localize_spanish_dialect import LocalizeSpanishDialect
 from .localize_portuguese_dialect import LocalizePortugueseDialect
+from .localize_french_dialect import LocalizeFrenchDialect
 
-LocalizeDialect = typing.Union[LocalizeEnglishDialect, LocalizeSpanishDialect, LocalizePortugueseDialect]
+LocalizeDialect = typing.Union[
+    LocalizeEnglishDialect, LocalizeSpanishDialect, LocalizePortugueseDialect, LocalizeFrenchDialect
+]

cartesia/voices/types/localize_french_dialect.py

@@ -0,0 +1,5 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+LocalizeFrenchDialect = typing.Union[typing.Literal["eu", "ca"], typing.Any]

cartesia/voices/types/localize_voice_request.py

@@ -1,17 +1,30 @@
 # This file was auto-generated by Fern from our API Definition.
 
 from ...core.pydantic_utilities import UniversalBaseModel
-from ...embedding.types.embedding import Embedding
+import pydantic
 from .localize_target_language import LocalizeTargetLanguage
 from .gender import Gender
 import typing
 from .localize_dialect import LocalizeDialect
 from ...core.pydantic_utilities import IS_PYDANTIC_V2
-import pydantic
 
 
 class LocalizeVoiceRequest(UniversalBaseModel):
-    embedding: Embedding
+    voice_id: str = pydantic.Field()
+    """
+    The ID of the voice to localize.
+    """
+
+    name: str = pydantic.Field()
+    """
+    The name of the new localized voice.
+    """
+
+    description: str = pydantic.Field()
+    """
+    The description of the new localized voice.
+    """
+
     language: LocalizeTargetLanguage
     original_speaker_gender: Gender
     dialect: typing.Optional[LocalizeDialect] = None

cartesia/voices/types/voice.py

@@ -2,9 +2,9 @@
 
 from ...core.pydantic_utilities import UniversalBaseModel
 from .voice_id import VoiceId
-import typing
 import pydantic
 import datetime as dt
+import typing
 from ...embedding.types.embedding import Embedding
 from ...tts.types.supported_language import SupportedLanguage
 from ...core.pydantic_utilities import IS_PYDANTIC_V2
@@ -12,14 +12,9 @@ from ...core.pydantic_utilities import IS_PYDANTIC_V2
 
 class Voice(UniversalBaseModel):
     id: VoiceId
-    user_id: typing.Optional[str] = pydantic.Field(default=None)
-    """
-    The ID of the user who owns the voice.
+    is_owner: bool = pydantic.Field()
     """
-
-    is_public: bool = pydantic.Field()
-    """
-    Whether the voice is publicly accessible.
+    Whether the current user is the owner of the voice.
     """
 
     name: str = pydantic.Field()
@@ -37,7 +32,16 @@ class Voice(UniversalBaseModel):
     The date and time the voice was created.
     """
 
-    embedding: Embedding
+    embedding: typing.Optional[Embedding] = pydantic.Field(default=None)
+    """
+    The vector embedding of the voice. Only included when `expand` includes `embedding`.
+    """
+
+    is_starred: typing.Optional[bool] = pydantic.Field(default=None)
+    """
+    Whether the current user has starred the voice. Only included when `expand` includes `is_starred`.
+    """
+
     language: SupportedLanguage
 
     if IS_PYDANTIC_V2:

cartesia/voices/types/voice_expand_options.py

@@ -0,0 +1,5 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+VoiceExpandOptions = typing.Union[typing.Literal["embedding", "is_starred"], typing.Any]

{cartesia-2.0.0b2.dist-info → cartesia-2.0.0b8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: cartesia
-Version: 2.0.0b2
+Version: 2.0.0b8
 Summary: 
 Requires-Python: >=3.8,<4.0
 Classifier: Intended Audience :: Developers
@@ -47,53 +47,6 @@ Our complete API documentation can be found [on docs.cartesia.ai](https://docs.c
 pip install cartesia
 ```
 
-## Reference
-
-A full reference for this library is available [here](./reference.md).
-
-## Voices
-
-```python
-from cartesia import Cartesia
-import os
-
-client = Cartesia(api_key=os.getenv("CARTESIA_API_KEY"))
-
-# Get all available voices
-voices = client.voices.list()
-print(voices)
-
-# Get a specific voice
-voice = client.voices.get(id="a0e99841-438c-4a64-b679-ae501e7d6091")
-print("The embedding for", voice.name, "is", voice.embedding)
-
-# Clone a voice using file data
-cloned_voice = client.voices.clone(
-    clip=open("path/to/voice.wav", "rb"),
-    name="Test cloned voice", 
-    language="en",
-    mode="similarity",  # or "stability"
-    enhance=False, # use enhance=True to clean and denoise the cloning audio
-    description="Test voice description"
-)
-
-# Mix voices together
-mixed_voice = client.voices.mix(
-    voices=[
-        {"id": "voice_id_1", "weight": 0.25},
-        {"id": "voice_id_2", "weight": 0.75}
-    ]
-)
-
-# Create a new voice from embedding
-new_voice = client.voices.create(
-    name="Test Voice",
-    description="Test voice description",
-    embedding=[...],  # List[float] with 192 dimensions
-    language="en"
-)
-```
-
 ## Usage
 
 Instantiate and use the client with the following:
@@ -107,15 +60,11 @@ client = Cartesia(
     api_key=os.getenv("CARTESIA_API_KEY"),
 )
 client.tts.bytes(
-    model_id="sonic-english",
+    model_id="sonic-2",
     transcript="Hello, world!",
     voice={
         "mode": "id",
         "id": "694f9389-aac1-45b6-b726-9d9369183238",
-        "experimental_controls": {
-            "speed": 0.5,  # range between [-1.0, 1.0], or "slow", "fastest", etc.
-            "emotion": ["positivity", "curiosity:low"] # list of emotions with optional intensity
-        }
     },
     language="en",
     output_format={
@@ -143,7 +92,7 @@ client = AsyncCartesia(
 
 async def main() -> None:
     async for output in client.tts.bytes(
-        model_id="sonic-english",
+        model_id="sonic-2",
         transcript="Hello, world!",
         voice={"id": "694f9389-aac1-45b6-b726-9d9369183238"},
         language="en",
@@ -176,7 +125,7 @@ except ApiError as e:
 
 ## Streaming
 
-The SDK supports streaming responses, as well, the response will be a generator that you can loop over.
+The SDK supports streaming responses as well, returning a generator that you can iterate over with a `for ... in ...` loop:
 
 ```python
 from cartesia import Cartesia
@@ -188,7 +137,7 @@ def get_tts_chunks():
         api_key=os.getenv("CARTESIA_API_KEY"),
     )
     response = client.tts.sse(
-        model_id="sonic",
+        model_id="sonic-2",
         transcript="Hello world!",
         voice={
             "id": "f9836c6e-a0bd-460e-9d3c-f7299fa60f94",
@@ -204,7 +153,7 @@ def get_tts_chunks():
             "sample_rate": 44100,
         },
     )
-    
+
     audio_chunks = []
     for chunk in response:
         audio_chunks.append(chunk)
@@ -215,7 +164,9 @@ for chunk in chunks:
     print(f"Received chunk of size: {len(chunk.data)}")
 ```
 
-## WebSocket
+## WebSockets
+
+For the lowest latency in advanced usecases (such as streaming in an LLM-generated transcript and streaming out audio), you should use our websockets client:
 
 ```python
 from cartesia import Cartesia
@@ -223,15 +174,10 @@ from cartesia.tts import TtsRequestEmbeddingSpecifierParams, OutputFormat_RawPar
 import pyaudio
 import os
 
-client = Cartesia(
-    api_key=os.getenv("CARTESIA_API_KEY"),
-)
+client = Cartesia(api_key=os.getenv("CARTESIA_API_KEY"))
 voice_id = "a0e99841-438c-4a64-b679-ae501e7d6091"
 transcript = "Hello! Welcome to Cartesia"
 
-# You can check out our models at https://docs.cartesia.ai/getting-started/available-models
-model_id = "sonic"
-
 p = pyaudio.PyAudio()
 rate = 22050
 
@@ -242,14 +188,14 @@ ws = client.tts.websocket()
 
 # Generate and stream audio using the websocket
 for output in ws.send(
-    model_id=model_id,
+    model_id="sonic-2", # see: https://docs.cartesia.ai/getting-started/available-models
     transcript=transcript,
     voice={"id": voice_id},
     stream=True,
     output_format={
         "container": "raw",
-        "encoding": "pcm_f32le", 
-        "sample_rate": 22050
+        "encoding": "pcm_f32le",
+        "sample_rate": rate
     },
 ):
     buffer = output.audio
@@ -267,6 +213,90 @@ p.terminate()
 ws.close()  # Close the websocket connection
 ```
 
+## Voices
+
+List all available Voices with `client.voices.list`, which returns an iterable that automatically handles pagination:
+
+```python
+from cartesia import Cartesia
+import os
+
+client = Cartesia(api_key=os.getenv("CARTESIA_API_KEY"))
+
+# Get all available Voices
+voices = client.voices.list()
+for voice in voices:
+    print(voice)
+```
+
+You can also get the complete metadata for a specific Voice, or make a new Voice by cloning from an audio sample:
+
+```python
+# Get a specific Voice
+voice = client.voices.get(id="a0e99841-438c-4a64-b679-ae501e7d6091")
+print("The embedding for", voice.name, "is", voice.embedding)
+
+# Clone a Voice using file data
+cloned_voice = client.voices.clone(
+    clip=open("path/to/voice.wav", "rb"),
+    name="Test cloned voice",
+    language="en",
+    mode="similarity",  # or "stability"
+    enhance=False, # use enhance=True to clean and denoise the cloning audio
+    description="Test voice description"
+)
+```
+
+## Requesting Timestamps
+
+```python
+import asyncio
+from cartesia import AsyncCartesia
+import os
+
+async def main():
+    client = AsyncCartesia(api_key=os.getenv("CARTESIA_API_KEY"))
+
+    # Connect to the websocket
+    ws = await client.tts.websocket()
+
+    # Generate speech with timestamps
+    output_generate = await ws.send(
+        model_id="sonic-2",
+        transcript="Hello! Welcome to Cartesia's text-to-speech.",
+        voice={"id": "f9836c6e-a0bd-460e-9d3c-f7299fa60f94"},
+        output_format={
+            "container": "raw",
+            "encoding": "pcm_f32le",
+            "sample_rate": 44100
+        },
+        add_timestamps=True,            # Enable word-level timestamps
+        add_phoneme_timestamps=True,    # Enable phonemized timestamps
+        stream=True
+    )
+
+    # Process the streaming response with timestamps
+    all_words = []
+    all_starts = []
+    all_ends = []
+    audio_chunks = []
+
+    async for out in output_generate:
+        # Collect audio data
+        if out.audio is not None:
+            audio_chunks.append(out.audio)
+
+        # Process timestamp data
+        if out.word_timestamps is not None:
+            all_words.extend(out.word_timestamps.words)    # List of words
+            all_starts.extend(out.word_timestamps.start)   # Start time for each word (seconds)
+            all_ends.extend(out.word_timestamps.end)       # End time for each word (seconds)
+
+    await ws.close()
+
+asyncio.run(main())
+```
+
 ## Advanced
 
 ### Retries
@@ -309,6 +339,26 @@ client.tts.bytes(..., request_options={
 })
 ```
 
+### Mixing voices and creating from embeddings
+
+```python
+# Mix voices together
+mixed_voice = client.voices.mix(
+    voices=[
+        {"id": "voice_id_1", "weight": 0.25},
+        {"id": "voice_id_2", "weight": 0.75}
+    ]
+)
+
+# Create a new voice from embedding
+new_voice = client.voices.create(
+    name="Test Voice",
+    description="Test voice description",
+    embedding=[...],  # List[float] with 192 dimensions
+    language="en"
+)
+```
+
 ### Custom Client
 
 You can override the `httpx` client to customize it for your use-case. Some common use-cases include support for proxies
@@ -326,13 +376,39 @@ client = Cartesia(
 )
 ```
 
+## Reference
+
+A full reference for this library is available [here](./reference.md).
+
 ## Contributing
 
-While we value open-source contributions to this SDK, this library is generated programmatically.
-Additions made directly to this library would have to be moved over to our generation code,
-otherwise they would be overwritten upon the next generated release. Feel free to open a PR as
-a proof of concept, but know that we will not be able to merge it as-is. We suggest opening
-an issue first to discuss with us!
+Note that most of this library is generated programmatically from
+<https://github.com/cartesia-ai/docs> — before making edits to a file, verify it's not autogenerated
+by checking for this comment at the top of the file:
+
+```
+# This file was auto-generated by Fern from our API Definition.
+```
+
+### Running tests
+
+```sh
+uv pip install -r requirements.txt
+uv run pytest -rP -vv tests/custom/test_client.py::test_get_voices
+```
+### Manually generating SDK code from docs
+
+Assuming all your repos are cloned into your home directory:
+
+```sh
+$ cd ~/docs
+$ fern generate --group python-sdk --log-level debug --api version-2024-11-13 --preview
+$ cd ~/cartesia-python
+$ git pull ~/docs/fern/apis/version-2024-11-13/.preview/fern-python-sdk
+$ git commit --amend -m "manually regenerate from docs" # optional
+```
+
+### Automatically generating new SDK releases
 
-On the other hand, contributions to the README are always very welcome!
+From https://github.com/cartesia-ai/docs click `Actions` then `Release Python SDK`. (Requires permissions.)