## Classes | Class | Description | |---|---| | [AudioClassifier](https://developers.google.com/edge/api/mediapipe/js/tasks-audio.audioclassifier) | Performs audio classification. | | [AudioTranscriber](https://developers.google.com/edge/api/mediapipe/js/tasks-audio.audiotranscriber) | MediaPipe Audio Task that performs automatic speech recognition (ASR) in unary and streaming modes via WASM SIMD or WebGPU. | | [FilesetResolver](https://developers.google.com/edge/api/mediapipe/js/tasks-audio.filesetresolver) | Resolves the files required for the MediaPipe Task APIs. The returned filesets require that the Wasm files are published without renaming. If this is not possible, you can invoke the MediaPipe Tasks APIs using a manually created `WasmFileset`. | | [TextToSpeech](https://developers.google.com/edge/api/mediapipe/js/tasks-audio.texttospeech) | MediaPipe Audio Task that performs neural text-to-speech synthesis in unary and streaming modes via WASM SIMD or WebGPU. | | [TextToSpeechStream](https://developers.google.com/edge/api/mediapipe/js/tasks-audio.texttospeechstream) | Active streaming synthesis session returned by `TextToSpeech.synthesizeStream()`. Supports both pull-based `readNext()` and `for await (const chunk of stream)` iteration, as well as incremental text input via `pushText()` and `finishInput()`. | ## Interfaces | Interface | Description | |---|---| | [AudioClassifierOptions](https://developers.google.com/edge/api/mediapipe/js/tasks-audio.audioclassifieroptions) | Options to configure the MediaPipe Audio Classifier Task | | [AudioClassifierResult](https://developers.google.com/edge/api/mediapipe/js/tasks-audio.audioclassifierresult) | Classification results of a model. | | [AudioTranscriberOptions](https://developers.google.com/edge/api/mediapipe/js/tasks-audio.audiotranscriberoptions) | Options to configure the MediaPipe AudioTranscriber Task on the Web. | | [AudioTranscriberResult](https://developers.google.com/edge/api/mediapipe/js/tasks-audio.audiotranscriberresult) | Result of an AudioTranscriber invocation. | | [Category](https://developers.google.com/edge/api/mediapipe/js/tasks-audio.category) | A classification category. | | [Classifications](https://developers.google.com/edge/api/mediapipe/js/tasks-audio.classifications) | Classification results for a given classifier head. | | [SynthesisOptions](https://developers.google.com/edge/api/mediapipe/js/tasks-audio.synthesisoptions) | Per-utterance synthesis overrides passed to `TextToSpeech.synthesize()` and `TextToSpeech.synthesizeStream()`. | | [TextToSpeechAudioChunk](https://developers.google.com/edge/api/mediapipe/js/tasks-audio.texttospeechaudiochunk) | A single streaming PCM audio chunk emitted by `TextToSpeechStream`. | | [TextToSpeechOptions](https://developers.google.com/edge/api/mediapipe/js/tasks-audio.texttospeechoptions) | Options to configure the MediaPipe TextToSpeech Task on the Web. | | [TextToSpeechResult](https://developers.google.com/edge/api/mediapipe/js/tasks-audio.texttospeechresult) | Result of a unary `TextToSpeech.synthesize()` invocation. | | [TranscriptionSegment](https://developers.google.com/edge/api/mediapipe/js/tasks-audio.transcriptionsegment) | A single transcribed segment emitted by AudioTranscriber. | | [VoiceInfo](https://developers.google.com/edge/api/mediapipe/js/tasks-audio.voiceinfo) | Voice metadata descriptor returned by `TextToSpeech.listVoices()`. | | [WordTimestamp](https://developers.google.com/edge/api/mediapipe/js/tasks-audio.wordtimestamp) | Word-level timing alignment mapping an input word to audio seconds. | ## Type Aliases | Type Alias | Description | |---|---| | [AudioTranscriberModelArchitecture](https://developers.google.com/edge/api/mediapipe/js/tasks-audio#audiotranscribermodelarchitecture) | Model architecture family for AudioTranscriber. | ## AudioTranscriberModelArchitecture {#audiotranscribermodelarchitecture} Model architecture family for AudioTranscriber. **Signature:** export declare type AudioTranscriberModelArchitecture = "AUTO" | "OMNI" | "TINY_GEMMA";