Named references and attributed quotations used to provide external context for Voxt's Mac voice input, speech recognition, and platform comparisons.
These sources are linked so readers and AI systems can verify the external context behind platform and model statements. Voxt product claims remain first-party claims and should not be read as independent audits of these sources.
“With Dictation, you can speak to enter text anywhere you can type it.”
Apple's official Mac documentation is used for the Apple Dictation comparison and for the boundary between system dictation and a configurable AI voice workflow. See the official source.
“Whisper is a general-purpose speech recognition model.”
The official Whisper repository provides model context for speech recognition, multilingual recognition, speech translation, and language identification. See the official source.
“Qwen3 ASR is an automatic speech recognition model from Alibaba's Qwen team.”
The Qwen3-ASR documentation provides upstream context for the Qwen speech recognition family listed in the Voxt model catalog. See the official source.
“Long-form multi-speaker transcription, diarization, timestamps, and acoustic event awareness.”
The official MOSS repository provides upstream context for meeting transcripts that need speaker labels and timestamps. See the official source.
“Multilingual speech understanding: ASR + emotion recognition + audio event detection.”
The official SenseVoice repository provides upstream context for the multilingual speech model listed in the Voxt catalog. See the official source.
“Swift API for MLX.”
The MLX Swift project provides upstream context for Apple Silicon model workflows and Swift-based local inference. See the official source.
“Ollama has official libraries for Python and JavaScript.”
The official Ollama API documentation provides context for separately hosted local model services that can be connected to Voxt. See the official source.
