Add language support to Cartesia synthesizer

[cyrilS-dev]

Description

This PR addresses an error introduced by PR #700 which added timestamps to the Cartesia synthesizer. The previous change resulted in an error when generating audio due to a missing language specification. This PR adds proper language support to the Cartesia synthesizer, resolving the error and allowing users to specify the language for text-to-speech synthesis.

Issue Fixed

Error message resolved: "Failed to generate audio: Error generating audio: error processing TTS request: Language must be specified for timestamps."

Changes

• Added language attribute to CartesiaSynthesizerConfig
• Updated CartesiaSynthesizer to use the specified language
• Modified the create_speech_uncached method to include language in the Cartesia API call

Testing

• Tested with French language setting :

synthesizer=CartesiaSynthesizer(
            synthesizer_config=CartesiaSynthesizerConfig.from_output_device(
                output_device=output_device,
                model_id = "sonic-multilingual",
                voice_id = "65b25c5d-ff07-4687-a04c-da2f43ef6fa9",
                language="fr",
            )
        ),

• Verified that the Cartesia API correctly receives and processes the language parameter

[chongzluong]

Apologies, appreciate the catch here!

[github-actions]

This PR has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.

[github-actions]

This PR has been automatically closed due to inactivity. Thank you for your contributions.