Back to tapWhisper

Model Directory Profile

Supported On-Device Models

tapWhisper is designed to run entirely offline and on-device for maximum privacy and performance. Explore the models supported by our engine.

Apple Inc.
1 variant

Apple Speech on macOS

Apple Speech is the default, zero-configuration transcription engine in tapWhisper.

View Model Specs →
OpenAI (original weights), GGML / whisper.cpp community (quantized files)
16 variants

OpenAI Whisper GGML

Whisper is OpenAI's state-of-the-art general-purpose speech recognition model.

View Model Specs →
Useful Sensors
2 variants

Useful Sensors Moonshine

Moonshine is a highly optimized, low-latency speech recognition model designed for real-time dictation on resource-constrained devices.

View Model Specs →
NVIDIA (NeMo team), Sherpa ONNX community
1 variant

NVIDIA Parakeet ONNX

NVIDIA's Parakeet is a state-of-the-art speech-to-text model optimized for English.

View Model Specs →
NVIDIA (NeMo team), Sherpa ONNX community
1 variant

NVIDIA Canary ONNX

NVIDIA's Canary is an advanced multi-lingual speech-to-text and translation model.

View Model Specs →
Google DeepMind
4 variants

Google Gemma Audio

Gemma Audio is a native end-to-end audio-to-text model.

View Model Specs →
Alibaba Group / llama.cpp community
4 variants

Alibaba Qwen 3 Formatter

Qwen 3 is a family of lightweight, high-performance language models (0.

View Model Specs →