Language guide · German de

Best local speech-to-text models for German

20 of the 26 reviewed local speech-to-text models explicitly list German. 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. 5 models offer native streaming, 3 native speaker diarization and 16 have a permissive license.

Top matches by setup

Computed with the same deterministic matcher as the homepage, restricted to models whose official source lists German. 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.

Best-ranked model from each of the top three model families, German
Setup	#1	#2	#3
Long recordings, 8–12 GB NVIDIA GPU, balanced	Whisper turbo 79/100 · Strong fit	Parakeet TDT 0.6B v3 79/100 · Strong fit	Orukeet 79/100 · Strong fit
Live transcription (native streaming, speed first)	Nemotron 3.5 ASR Streaming 0.6B 91/100 · Excellent fit	Voxtral Mini 4B Realtime 2602 86/100 · Excellent fit	VibeVoice-ASR Streaming 1.5B 83/100 · Strong fit
Meetings with speaker labels (diarization + timestamps)	VibeVoice-ASR 7B 86/100 · Excellent fit	Whisper medium 84/100 · Strong fit	Parakeet TDT 0.6B v3 84/100 · Strong fit
Subtitles with timing, accuracy first	Whisper medium 87/100 · Excellent fit	Parakeet TDT 0.6B v3 83/100 · Strong fit	Orukeet 83/100 · Strong fit
CPU-only machine, low memory use	Parakeet Redux 78/100 · Strong fit	Whisper tiny 74/100 · Strong fit	Whistle 71/100 · Possible fit

Re-rank for your setup

Change hardware, workload and requirements to re-rank all 20 German-capable models in your browser.

Choose by requirement

Live captions and voice input: Native streaming: Nemotron 3.5 ASR Streaming 0.6B, 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, Omnilingual ASR CTC 300M, Cohere Transcribe 03-2026, VibeVoice-ASR 7B, VibeVoice-ASR Streaming 1.5B, Voxtral Mini 4B Realtime 2602, Granite Speech 5.0 2B, Granite Speech 5.0 470M TurboCTC, VibeVoice-ASR-Streaming-7B and Whistle. 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, Granite Speech 5.0 470M TurboCTC, Parakeet Redux and Whistle.

All 20 models that list German

Reviewed local ASR models listing German
Model	Streaming	Timestamps	Diarization	License	CPU · NVIDIA fit
Cohere Transcribe 03-2026 Cohere Labs · 2B	No	Limited	No	Apache-2.0 Permissive	1/5 · 5/5
Granite Speech 5.0 2B IBM · 2B	No	No	No	Apache-2.0 Permissive	2/5 · 5/5
Granite Speech 5.0 470M TurboCTC IBM · 470M	No	No	No	Apache-2.0 Permissive	4/5 · 4/5
Nemotron 3.5 ASR Streaming 0.6B NVIDIA · 600M	Native	Limited	No	OpenMDW-1.1 Custom terms	2/5 · 5/5
Omnilingual ASR CTC 300M Meta AI · 325M	No	Limited	No	Apache-2.0 Permissive	3/5 · 5/5
Orukeet Oruk AI · 627M	No	Yes	No	CC BY-SA 4.0 Attribution + ShareAlike	3/5 · 5/5
Parakeet Redux Moondream · 1.58-bit Parakeet 0.6B (178 MB)	No	No	No	CC BY 4.0 Attribution required	5/5 · 3/5
Parakeet TDT 0.6B v3 NVIDIA · 600M	Via runtime	Yes	No	CC BY 4.0 Attribution required	2/5 · 5/5
Qwen3-ASR 0.6B Qwen · 0.6B	Via runtime	Separate aligner	No	Apache-2.0 Permissive	2/5 · 5/5
Qwen3-ASR 1.7B Qwen · 1.7B	Via runtime	Separate aligner	No	Apache-2.0 Permissive	1/5 · 5/5
VibeVoice-ASR 7B Microsoft · 9B total	No	Yes	Yes	MIT Permissive	1/5 · 4/5
VibeVoice-ASR Streaming 1.5B Microsoft · 3B total	Native	Limited	Yes	MIT Permissive	1/5 · 4/5
VibeVoice-ASR-Streaming-7B Microsoft · 9B total	Native	Limited	Yes	MIT Permissive	1/5 · 4/5
Voxtral Mini 4B Realtime 2602 Mistral AI · 4B	Native	Limited	No	Apache-2.0 Permissive	1/5 · 5/5
Whisper base OpenAI · 74M	Via runtime	Yes	No	MIT Permissive	5/5 · 4/5
Whisper medium OpenAI · 769M	Via runtime	Yes	No	MIT Permissive	2/5 · 5/5
Whisper small OpenAI · 244M	Via runtime	Yes	No	MIT Permissive	4/5 · 5/5
Whisper tiny OpenAI · 39M	Via runtime	Yes	No	MIT Permissive	5/5 · 4/5
Whisper turbo OpenAI · 809M	Via runtime	Yes	No	MIT Permissive	2/5 · 5/5
Whistle Cactus Compute · 16.9 MB file (parameters not stated)	Native	Yes	No	Apache-2.0 Permissive	5/5 · 2/5

Multilingual models that do not list German

VibeVoice-ASR-BitNet, Fun-ASR-MLT-Nano-2512 and Jais-ASR are multilingual but do not list German in the reviewed official source, so the matcher does not recommend them for this language.

Common questions

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

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 Parakeet Redux for CPU-only machines. Benchmark the top two or three on your own German audio before deciding.

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

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

Does Whisper support German?

Yes. All Whisper sizes list German 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 German?

Among multilingual models, VibeVoice-ASR-BitNet, Fun-ASR-MLT-Nano-2512 and Jais-ASR do not list German in their reviewed sources. English-only models are also excluded.

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