# Structures

The following declarations are available globally.
- `
  ### [AudioChunk](https://developers.google.com/edge/api/mediapipe/swift/audio/Structs/AudioChunk.md.txt)

  ` Incremental mono PCM audio chunk emitted by `TextToSpeech.synthesizeStream(_:options:)`.

  #### Declaration

  Swift

      struct AudioChunk: Sendable, Equatable

- `
  ### [AudioResult](https://developers.google.com/edge/api/mediapipe/swift/audio/Structs/AudioResult.md.txt)

  ` Self-contained mono PCM audio buffer returned by `TextToSpeech.synthesize(_:options:)`.

  #### Declaration

  Swift

      struct AudioResult: Sendable, Equatable

- `
  ### [SynthesisOptions](https://developers.google.com/edge/api/mediapipe/swift/audio/Structs/SynthesisOptions.md.txt)

  ` Per-utterance synthesis overrides passed to `TextToSpeech.synthesize(_:options:)` and `TextToSpeech.synthesizeStream(_:options:)`. Both fields default to `nil` so non-English voices (e.g. `"ef_dora"`, `"zf_xiaobei"`) automatically infer their native language from the voice metadata.

  #### Declaration

  Swift

      struct SynthesisOptions: Sendable, Equatable

- `
  ### [TTSBaseOptions](https://developers.google.com/edge/api/mediapipe/swift/audio/Structs/TTSBaseOptions.md.txt)

  ` MediaPipe Tasks-harmonized base options for `.litertlm` model loading and hardware delegation.

  #### Declaration

  Swift

      struct TTSBaseOptions: Sendable, Equatable

- `
  ### [TextToSpeechOptions](https://developers.google.com/edge/api/mediapipe/swift/audio/Structs/TextToSpeechOptions.md.txt)

  ` Task initialization options for `TextToSpeech` (backed by LiteRT-LM Omni Kokoro-82M).

  #### Declaration

  Swift

      struct TextToSpeechOptions: Sendable, Equatable

- `
  ### [VoiceInfo](https://developers.google.com/edge/api/mediapipe/swift/audio/Structs/VoiceInfo.md.txt)

  ` Voice metadata descriptor returned by `TextToSpeech.listVoices()`.

  #### Declaration

  Swift

      struct VoiceInfo: Sendable, Equatable

- `
  ### [WordTimestamp](https://developers.google.com/edge/api/mediapipe/swift/audio/Structs/WordTimestamp.md.txt)

  ` Word-level timing alignment mapping an input word to audio seconds.

  #### Declaration

  Swift

      struct WordTimestamp: Sendable, Equatable