Audio transcription guide

The MediaPipe Audio Transcriber task lets you turn speech into text on the device. You can use this task to add live captions, dictation, voice notes, or voice commands to your app. This task operates on audio data with a machine learning (ML) model, either as a complete audio clip or as a continuous stream, and outputs transcript segments with timestamps. While audio is streaming, the task can also return interim results that are refined as more audio arrives.

Note: Please ensure you process voice data responsibly and in accordance with applicable law.

Get Started

Start using this task by following one of these implementation guides for your target platform. These platform-specific guides walk you through a basic implementation of this task, including a recommended model, and code example with recommended configuration options:

Platform	Code Example	Guide
Android	Code example	Guide
iOS	Code example	Guide

Task details

This section describes the capabilities, inputs, outputs, and configuration options of this task.

Features

• Streaming transcription - Pass audio in small chunks, for example from the microphone, and get transcript segments back while the user speaks.
• Audio clip transcription - Transcribe a complete recording in a single call.
• Interim results - Optionally get early, non-final hypotheses for low-latency captions. The task replaces them with final segments as more audio arrives.
• Segment timestamps - Each segment includes its start and end time in the audio.
• Prewarming - Load the model ahead of time to reduce the latency of the first result.
• On-device processing - The task processes audio entirely on the device and doesn't send audio or transcripts off the device.

Task inputs	Task outputs
Input is mono PCM audio as float samples in the range [-1.0, 1.0], provided as one of the following: Audio clip Audio stream	Audio Transcriber outputs a list of transcript segments containing: Transcript: the recognized text of the segment Final flag: whether the segment is final or an interim hypothesis Timestamps: the start and end time of the segment in the audio, in milliseconds

Configurations options

This task has the following configuration options:

Option Name	Description	Value Range	Default Value
modelAssetPath	Absolute path to the speech recognition model file (.litertlm) on the device. Set this option in the base options. You can also pass a file descriptor with setModelAssetFileDescriptor. In-memory model buffers aren't supported.	File path	None (required)
delegate	Hardware used to run the model. Set this option in the base options.	{Delegate.CPU, Delegate.GPU}	CPU
sampleRateHz	Sample rate of the input audio, in Hz. If the input isn't 16000 Hz, the task resamples it to 16 kHz before transcribing it.	Positive number	16000
enableInterimResults	Whether to return interim segments while audio is streaming. Interim segments are early hypotheses that can change as more audio arrives. The task later returns a final segment for the same audio.	Boolean	false
modelArchitecture	Model family. With the default value, the task detects the model family from the model file. Use the open-weights value for models such as Parakeet.	{ModelArchitecture.AUTO, ModelArchitecture.OMNI}	ModelArchitecture.AUTO
cacheDir	Writable directory where the task caches compiled model artifacts, so that later starts are faster.	Directory path	Not set

Note: Interim results are returned only when enableInterimResults is set. Final segments are always returned.

Models

The Audio Transcriber requires a speech recognition model in the LiteRT-LM (.litertlm) format. The model isn't included in the MediaPipe Tasks libraries. Download the model from Hugging Face, store it on the device, and pass its local path to the task, as shown in the platform guides under Get Started.

Note: The model is large, about 615 MB. Instead of bundling it in your app package, download it the first time your app needs it and store it in app-specific storage. Keep the original filename. The task uses the filename or the model's metadata to detect the model type.

Parakeet TDT 0.6B v3 (recommended)

Parakeet TDT 0.6B v3 is an NVIDIA speech recognition model that transcribes 25 European languages and outputs punctuated, capitalized text.

Model name	Languages	Quantization type	Size	Versions
Parakeet TDT 0.6B v3	25 European languages	INT8	About 615 MB	Latest

Model license and attribution

NVIDIA publishes Parakeet TDT 0.6B v3 under the Creative Commons Attribution 4.0 (CC-BY-4.0) license. If you distribute an app that uses this model, give appropriate credit to NVIDIA, for example in your app's open source notices.

Task benchmarks

Benchmarks for the recommended model are coming soon.