v1.0.12

v1.0.12 (08-13-2024)

Features

• Adds support for voices.mix(...) to mix voices and get an embedding back

Fixes

• Removes duplicate import for websockets.sync.client.connect

v1.0.11

v1.0.11 (08-07-2024)

Features

• Support timestamps on _TTSContext.send on the sync Cartesia client
• Allow speed in _experimental_voice_controls to be specified as a float between [-1.0, 1.0]

Adds

• Expands testing suite

v1.0.9

v1.0.9 (07-25-2024)

Adds

• enhance param to the tts.voice.clone method which controls whether the sample clip submitted is enhanced prior to voice cloning

Chores

• Returns a warning on the synchronous _WebSocket class if the user's websockets version < 12.0

v1.0.7

v1.0.7 (07-15-2024)

Features

• Supports generating timestamps on the WebSocket endpoint to get detailed timing information for each word in input transcripts.
• Experimental support for applying speed & emotion controls on voices.

Adds

• add_timestamps param to _WebSocket.send(), _AsyncWebSocket.send(), _TTSContext.send() and _AsyncTTSContext.send() methods for generating timestamps corresponding to input transcripts.
  • Timestamp results are returned in a word_timestamps object with the keys: words, start and end
• _experimental_voice_controls param to all send() methods which accepts an object with speed and emotion fields

Chores

• Adds usage examples for feature updates to README

v1.0.5

v1.0.5 (07-12-2024)

Features

• Support for audio continuations on synchronous Cartesia client. Users can pass in a text generator to receive streaming audio.

Adds

• New _TTSContext class and context() method to _WebSocket for supporting input streaming use cases with continuations.
  • send() method that takes in an Iterator object as the transcript. Returns Generator that streams out audio data.

v1.0.4

v1.0.4 (07-06-2024)

Features

• Support for audio continuations for seamless speech synthesis. Allows real-time audio generation and playback as text becomes available.

Adds

• New _AsyncTTSContext class and context() method to _AsyncWebsocket for managing streaming sessions
  • send() method for streaming text inputs
  • no_more_inputs() method to signal the end of text input, which sends a message with continue_ = False. Otherwise, the context times out after 5 seconds of inactivity.
  • receive() method returns AsyncGenerator for asynchronous audio chunk retrieval
• Support for specifying custom base_url when initializing Cartesia or AsyncCartesia

Changes

• Modifies AsyncWebsocket to internally use the AsyncContext class. No change in usage.

Bug Fixes

• Removes Content-Type header from filepath cloning to work with httpx.post
• Fixes client.tts.get_output_format for deprecated output format names

v1.0.3

v1.0.3 (06-25-2024)

Changes

• Fixes undefined import issue for cartesia.utils by modifying setup.py to include subdirectories

v1.0.2

v1.0.2 (06-25-2024)

Chores

• Adds __init__ to cartesia/utils to make it a module

v1.0.1

v1.0.1 (06-25-2024)

Changes

• Updates OutputFormatMapping with more clearly-defined names that will be supported going forward.
  • This deprecates the old string-based names and moves them to DeprecatedOutputFormatMapping. These will be removed in v1.2.0
  • The usage remains the same by calling client.tts.get_output_format

Chores

• Adds utils.deprecated to allow using a @deprecated decorator for functions/methods that will be deprecated in future versions
• Adds usage docs for client.tts.get_output_format
• Updates documentation

v1.0.0

v1.0.0 (06-24-2024)

A new major version release of the Cartesia Python client that overhauls the library structure.

Refer to the migration guide for more thorough details on changes.

Features

• Adds support for model_id=sonic-multilingual to generate multilingual audio
• Endpoint-specific methods for generating and streaming audio

Breaking changes

• Renames CartesiaTTS and AsyncCartesiaTTS -> Cartesia and AsyncCartesia
• Replaces client.generate with endpoint-specific methods for Text-to-Speech
• output_format must be specified as an OutputFormat object, which is a dict specifying the keys: container, encoding and sample_rate
• Both SSE and WebSocket requests no longer return sampling_rate in their output. They will respect the sample_rate corresponding to the OutputFormat passed in.

Adds

• client.tts.sse methods for generating audio using Server-Sent Events
• client.tts.websocket methods for managing a WebSocket connection and generating audio
• client.tts.get_output_format() to obtain OutputFormat object from output format name
• client.tts.get_sample_rate() to obtain sample_rate from output format name
• client.voices.list() to fetch a list of all available voices
• client.voices.get() to fetch a VoiceMetadata object from voice_id
• client.voices.clone() to clone a voice by specifying a filepath
• client.voices.create() to create a new voice
• Specifies cartesia_version=2024-06-10 as default header for HTTP and WS requests

Removes

• client.get_voices()
• client.get_voice_embedding()
• client.generate()
• Ability to specify Numpy Array as a return type. We recommend using np.frombuffer with the appropriate dtype.
• Ability to clone voices using a link