Speaks params.text. params.CancellationToken is passed to the request, and reading the audio
stops as soon as it aborts; the failure is then classified as a cancellation.
The driver's speech models.
Retrieves all pronunciation dictionaries from ElevenLabs API. Implements automatic pagination to fetch all available dictionaries across multiple pages.
Promise resolving to array of all pronunciation dictionaries
The names of the methods this driver implements.
The voices the driver can speak in.
Transcribes the audio in params.audioData (or the base 64 params.audioFile). On success the
transcript is in SpeechResult.content, and SpeechResult.usage carries the audio duration in
Seconds when the provider reported one.
ProtectedTranscribeTranscribes audio that may exceed the provider's upload ceiling, splitting it first when it does. See TranscribeAudioWithSplitting, which this calls, for the behavior.
The full audio to transcribe
The provider's hard upload ceiling
Target piece size, below the ceiling to leave room for multipart framing
Splitter to use for oversized audio; may be null, in which case oversized audio fails
Provider name, used in the size-limit error messages
Transcribes a single piece already known to be within the ceiling, and is
handed cancellationToken to forward to its request
OptionalcancellationToken: AbortSignalCancels the transcription: no further piece is sent once it aborts
ElevenLabs text-to-speech, with voice and pronunciation-dictionary listing. It does not implement speech-to-text.
Registered against BaseTextToSpeech under the key model metadata names. It still extends, and is registered against,
BaseAudioGenerator, so callers that resolve it through the old base keep working.