Best local speech-to-text models for English

26 of the 26 reviewed local speech-to-text models explicitly list English. For long recordings on a mid-range NVIDIA GPU the matcher's first pick is Whisper turbo; for live transcription it is Nemotron 3.5 ASR Streaming 0.6B; for meetings with speaker labels it is VibeVoice-ASR 7B. 7 models offer native streaming, 3 native speaker diarization and 22 have a permissive license.

Top matches by setup

Computed with the same deterministic matcher as the homepage, restricted to models whose official source lists English. To keep the shortlist useful, each row shows the best-ranked model from three different families (for example, only one Whisper size). Scores are decision guidance, not accuracy claims.

Choose by requirement

Live captions and voice input

Native streaming: Nemotron 3.5 ASR Streaming 0.6B, Moonshine Tiny Streaming (English), Moonshine Medium Streaming (English), VibeVoice-ASR Streaming 1.5B, Voxtral Mini 4B Realtime 2602, VibeVoice-ASR-Streaming-7B and Whistle. Everything else needs a chunking runtime, which adds latency.

Speaker-labelled meetings

Native diarization: VibeVoice-ASR 7B, VibeVoice-ASR Streaming 1.5B and VibeVoice-ASR-Streaming-7B. Other models need a separate diarization pipeline.

Commercial products

Permissive licenses: Whisper (tiny, base, small, medium, turbo), Qwen3-ASR 0.6B, Qwen3-ASR 1.7B, Distil-Whisper large-v3, Moonshine Tiny Streaming (English), Moonshine Medium Streaming (English), Omnilingual ASR CTC 300M, Cohere Transcribe 03-2026, VibeVoice-ASR 7B, VibeVoice-ASR Streaming 1.5B, VibeVoice-ASR-BitNet, Fun-ASR-MLT-Nano-2512, Voxtral Mini 4B Realtime 2602, Granite Speech 5.0 2B, Granite Speech 5.0 470M TurboCTC, VibeVoice-ASR-Streaming-7B, Whistle and Jais-ASR. 4 other models carry attribution, ShareAlike or custom terms.

CPU-only or low-power machines

Rated 4/5 or better for CPU-only use: Whisper tiny, Whisper base, Whisper small, Moonshine Tiny Streaming (English), Moonshine Medium Streaming (English), VibeVoice-ASR-BitNet, Granite Speech 5.0 470M TurboCTC, Parakeet Redux and Whistle.

All 26 models that list English

English-only specialists

Distil-Whisper large-v3, Moonshine Tiny Streaming (English) and Moonshine Medium Streaming (English) transcribe English only. They are worth testing when you never need another language: the Moonshine models are built for low-latency, low-resource use, and Distil-Whisper is a faster distilled Whisper variant.

Common questions

What is the best local speech-to-text model for English?

There is no single winner; it depends on the workload. In the matcher, Whisper turbo leads for long recordings on a mid-range GPU, VibeVoice-ASR 7B for meetings with speaker labels and VibeVoice-ASR-BitNet for CPU-only machines. Benchmark the top two or three on your own English audio before deciding.

Is there an offline English model with real-time streaming?

Yes. Nemotron 3.5 ASR Streaming 0.6B, Moonshine Tiny Streaming (English), Moonshine Medium Streaming (English), VibeVoice-ASR Streaming 1.5B, Voxtral Mini 4B Realtime 2602, VibeVoice-ASR-Streaming-7B and Whistle list English and have a native streaming architecture. Measure end-to-end latency on your hardware.

Does Whisper support English?

Yes. All Whisper sizes list English in the official tokenizer language list. Smaller sizes trade accuracy for speed; Whisper turbo is the usual starting point on a GPU.

Which models do not support English?

Every reviewed multilingual model lists English.

Related

• Language support matrix for all 104 languages
• Best local speech-to-text models for multilingual use
• Measure English transcripts with the WER calculator
• Compare the top three side by side

Generated from the reviewed model database (latest review November 3, 2026). "Lists English" means the model's official source explicitly names the language; it does not guarantee equal accuracy across languages.