whatmodel.sh · find the best speech-to-text models you can run

Best multilingual speech-to-text models to run locally

A leaderboard of the best multilingual speech-to-text models you can run on your own computer. SeamlessM4T v2 Large is #1 right now, followed by Voxtral Small 24B (2507) and Cohere Transcribe (03-2026). Models are ranked on transcription tests in many languages. Each model shows the download that fits and the command to run it.

29 models · scores combine 7 benchmarks · updated how it works · find a leaderboard · benchmark your machine
task[all tasks][long-form transcription][multilingual transcription]

Scores use reviewed multilingual transcription evaluations only. Compare scores within this task. Models without task measurements are excluded.

Filter by your hardware and budget · local only · reset
+ more

Detect your exact chip or graphics card:

curl -G whatmodel.sh/stt -d max=0 --data-urlencode "mac=$(sysctl -n hw.memsize machdep.cpu.brand_string)"Mac

curl -G whatmodel.sh/stt -d max=0 --data-urlencode "ram=$(awk '/MemT/{print $2}' /proc/meminfo)" --data-urlencode "nv=$(nvidia-smi --query-gpu=name,memory.total --format=csv,noheader 2>/dev/null)"Linux

curl.exe -G whatmodel.sh/stt -d max=0 --data-urlencode "ram=$((gcim Win32_ComputerSystem).TotalPhysicalMemory)" --data-urlencode "nv=$(nvidia-smi --query-gpu=name,memory.total --format=csv,noheader 2>$null)"Windows

$ terminal

detecting your OS…

Run curl "whatmodel.sh/stt?max=0"to get this list in your terminal (add &format=json for agents).

ram[8][16][24][32][48][64][96][128][192][256]GB
gpu[apple silicon][graphics card][none]
price[local][$0.001][$0.002][$0.005][any]max per audio min

detecting your OS…

Score vs memory to run

#modeltask score↓where↓speed↓RAM↓get itsources
#modeltask score↓where↓speed↓RAM↓get itsources
2SeamlessM4T v2 Large Meta79±8*local~9.2GBhow to run › Benchmarking Automatic Speech Recognition Tools for Iberian Languages (arXiv:2609.36920v1), Table 3
6Voxtral Small 24B (2507) Mistral65±7*local~59GBhow to run › Open ASR LeaderboardCoSE-E: A Benchmark for Code-switched Speech Evaluation in Enterprise Settings (arXiv:2609.35645v1), Table 2
7Cohere Transcribe (03-2026) Cohere64±9*local~5.5GBhow to run › Open ASR Leaderboard
8Whisper large-v3 OpenAI61±6*local~4.2GBhow to run › Benchmarking Automatic Speech Recognition Tools for Iberian Languages (arXiv:2609.36920v1), Table 3Open ASR Leaderboard
10Omnilingual ASR LLM 7B v2 Meta59±9*local~19GBhow to run › Open ASR Leaderboard
12Omnilingual ASR LLM 1B v2 Meta59±6*local~6GBhow to run › Benchmarking Automatic Speech Recognition Tools for Iberian Languages (arXiv:2609.36920v1), Table 3Open ASR Leaderboard
13Voxtral Mini 3B (2507) Mistral57±6*local~12GBhow to run › Benchmarking Automatic Speech Recognition Tools for Iberian Languages (arXiv:2609.36920v1), Table 3Open ASR Leaderboard
14Omnilingual ASR LLM 7B Meta57±9*local~19GBhow to run › Open ASR Leaderboard
15Omnilingual ASR CTC 1B v2 Meta51±6*local~2.9GBhow to run › Benchmarking Automatic Speech Recognition Tools for Iberian Languages (arXiv:2609.36920v1), Table 3Open ASR Leaderboard
16Whisper large-v3-turbo OpenAI51±9*local~2.4GBhow to run › Open ASR Leaderboard
17Cohere Transcribe Arabic (07-2026) Cohere50±9*local~4.1GBhow to run › QCRI Arabic + English ASR leaderboard (Hugging Face Space QCRI/AURA-Arabic-English-ASR-leaderboard)
18Parakeet TDT 0.6B v3 NVIDIA49±6local~2GBhow to run › Benchmarking Automatic Speech Recognition Tools for Iberian Languages (arXiv:2609.36920v1), Table 3Open ASR LeaderboardCoSE-E: A Benchmark for Code-switched Speech Evaluation in Enterprise Settings (arXiv:2609.35645v1), Table 2
19Omnilingual ASR CTC 7B v2 Meta49±9*local~16GBhow to run › Open ASR Leaderboard
20Omnilingual ASR LLM 3B v2 Meta48±9*local~11GBhow to run › Open ASR Leaderboard
21Phi-4-multimodal-instruct Microsoft48±6*local~14GBhow to run › Benchmarking Automatic Speech Recognition Tools for Iberian Languages (arXiv:2609.36920v1), Table 3Open ASR Leaderboard
22Qwen3-ASR-1.7B Alibaba (Qwen)48±5local~3.3GBhow to run › Benchmarking Automatic Speech Recognition Tools for Iberian Languages (arXiv:2609.36920v1), Table 3QCRI Arabic + English ASR leaderboard (Hugging Face Space QCRI/AURA-Arabic-English-ASR-leaderboard)Open ASR Leaderboard
23Omnilingual ASR CTC 3B v2 Meta47±9*local~7.9GBhow to run › Open ASR Leaderboard
24Omnilingual ASR CTC 7B Meta47±9*local~16GBhow to run › Open ASR Leaderboard
25Omnilingual ASR LLM 3B Meta46±9*local~11GBhow to run › Open ASR Leaderboard
26Canary-1B-v2 NVIDIA46±6*local~5.2GBhow to run › Benchmarking Automatic Speech Recognition Tools for Iberian Languages (arXiv:2609.36920v1), Table 3Open ASR Leaderboard
27Omnilingual ASR LLM 1B Meta44±9*local~6GBhow to run › Open ASR Leaderboard
29Omnilingual ASR CTC 3B Meta41±9*local~7.9GBhow to run › Open ASR Leaderboard
30Qwen3-ASR-0.6B Alibaba (Qwen)38±7*local~2.8GBhow to run › QCRI Arabic + English ASR leaderboard (Hugging Face Space QCRI/AURA-Arabic-English-ASR-leaderboard)Open ASR Leaderboard
31Voxtral Mini 4B Realtime (2602) Mistral37±4local~3.2GBhow to run › Voxtral RealtimeBenchmarking Automatic Speech Recognition Tools for Iberian Languages (arXiv:2609.36920v1), Table 3Open ASR Leaderboard
33Omnilingual ASR LLM 300M v2 Meta35±9*local~4.4GBhow to run › Open ASR Leaderboard
34Omnilingual ASR CTC 1B Meta33±9*local~2.9GBhow to run › Open ASR Leaderboard
35Omnilingual ASR LLM 300M Meta31±9*local~4.4GBhow to run › Open ASR Leaderboard
36Omnilingual ASR CTC 300M v2 Meta14±9*local~1.3GBhow to run › Open ASR Leaderboard
37Omnilingual ASR CTC 300M Meta12±9*local~1.3GBhow to run › Open ASR Leaderboard

+ 8 more don't fit your machine or budget · show them

37 of 37 catalogue models listed here · sources and licences

* new or thinly tested: ranked on too few benchmark results · † only the maker’s own numbers so far · ~RAM is estimated; full context may need more memory