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

Best speech-to-text models for long recordings for a 16GB Mac

A leaderboard of the best speech-to-text models for long recordings for a Mac with 16GB of memory. The best one that runs on it right now is Whisper large-v3, followed by Whisper large-v3-turbo and Parakeet TDT 0.6B v2. Models are ranked on transcription tests with long recordings. Models that run on it show the download that fits and the command to run it.

18 models · scores combine 1 benchmarks · updated how it works · find a leaderboard · benchmark your machine
task[all tasks][long-form transcription][multilingual transcription]

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

Models for 16GB RAM · Apple Silicon → ~11GB fast · reset
+ more
chip[M1][M1 Pro][M2][M2 Pro][M3][M4][M5][M6 (16GB)]
set[all sets][Open ASR English long-form WER · 31][Voxtral report · English long-form 4-set WER · 4]

Filter the model list while keeping task scores. Models without a shared score scale are not yet calibrated; select a set to see its own scores.

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?ram=16&gpu=apple"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 API price

#modeltask score↓where↓speed↓RAM↓get itsources
#modeltask score↓where↓speed↓RAM↓get itsources
2Scribe v2 ElevenLabs76±10*api $0.0037/audio minelevenlabs.io ↗Open ASR Leaderboard
4Speechmatics Enhanced Speechmatics69±10*api $0.0067/audio minwww.speechmatics.com ↗Open ASR Leaderboard
5Cohere Transcribe (03-2026) Cohere63±10*api $0.0042/audio minfal.ai ↗Open ASR Leaderboard
8Whisper large-v3 · fp16 OpenAI58±10*local~4.2GBhow to run › Open ASR Leaderboard
9Whisper large-v3-turbo · fp16 OpenAI58±10*local~2.4GBhow to run › Open ASR Leaderboard
10Rev AI Machine (Reverb ASR) Rev58±10*api $0.0033/audio mindocs.rev.ai ↗Open ASR Leaderboard
11Parakeet TDT 0.6B v2 · onnx-fp32 NVIDIA56±10*local~3.4GBhow to run › Open ASR Leaderboard
12Parakeet TDT 0.6B v3 · onnx-fp32 NVIDIA55±10*local~3.5GBhow to run › Open ASR Leaderboard
14Whisper large (v1) · fp32 OpenAI54±10*local~7.9GBhow to run › Open ASR Leaderboard
15Whisper large-v2 · fp32 OpenAI54±10*local~7.9GBhow to run › Open ASR Leaderboard
17Chirp 3 Google53±10*api price unknowncloud.google.com ↗Open ASR Leaderboard
20Distil-Whisper distil-large-v3 · fp16 Hugging Face (Distil-Whisper)51±10*local~2.3GBhow to run › Open ASR Leaderboard
26Distil-Whisper distil-large-v2 · fp16 Hugging Face (Distil-Whisper)30±10*local~2.3GBhow to run › Open ASR Leaderboard
31Distil-Whisper distil-medium.en · fp16 Hugging Face (Distil-Whisper)16±10*local~1.4GBhow to run › Open ASR Leaderboard
—GPT-4o Mini Transcribe OpenAInot yet calibratedapi $0.0030/audio mindevelopers.openai.com ↗Voxtral Realtime
—Kyutai STT 2.6B (en) · bf16 Kyutainot yet calibratedlocal~6.7GBhow to run › Voxtral Realtime
—Voxtral Mini 4B Realtime (2602) · 4bit Mistralnot yet calibratedlocal~3.2GBhow to run › Voxtral Realtime
—Voxtral Mini Transcribe V2 Mistralnot yet calibratedapi $0.0030/audio mindocs.mistral.ai ↗Voxtral Realtime

+ 17 more don't fit your machine or budget · show them

35 of 35 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