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

Best speech-to-text models for long recordings

A leaderboard of the best speech-to-text models for long recordings. Scribe v1 is #1 right now, followed by Scribe v2 and Universal-3 Pro. Models are ranked on transcription tests with long recordings. Filter by your computer or budget to find the best one you can use.

35 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.

Filter by your hardware and budget · reset
+ more
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/sttto 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
1Scribe v1 ElevenLabs78±10*comparison onlyOpen ASR Leaderboard
2Scribe v2 ElevenLabs76±10*api $0.0037/audio minelevenlabs.io ↗Open ASR Leaderboard
3Universal-3 Pro AssemblyAI70±10*comparison onlyOpen 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 min +local~5.5GBfal.ai ↗Open ASR Leaderboard
6Rev AI Fusion (Whisper Fusion) Rev59±10*comparison onlyOpen ASR Leaderboard
7Canary-Qwen-2.5B NVIDIA59±10*local~6.6GBhow to run › Open ASR Leaderboard
8Whisper large-v3 OpenAI58±10*api $0.0018/audio min +local~4.2GBconsole.groq.com ↗Open ASR Leaderboard
9Whisper large-v3-turbo OpenAI58±10*api $0.0005/audio min +local~2.4GBdevelopers.cloudflare.com ↗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 NVIDIA56±10*local~1.9GBhow to run › Open ASR Leaderboard
12Parakeet TDT 0.6B v3 NVIDIA55±10*api $0.0015/audio min +local~2GBwww.together.ai ↗Open ASR Leaderboard
13Parakeet CTC 1.1B NVIDIA54±10*local~5.6GBhow to run › Open ASR Leaderboard
14Whisper large (v1) OpenAI54±10*local~4.2GBhow to run › Open ASR Leaderboard
15Whisper large-v2 OpenAI54±10*local~4.2GBhow to run › Open ASR Leaderboard
16Parakeet RNNT 0.6B NVIDIA53±10*local~3.5GBhow to run › Open ASR Leaderboard
17Chirp 3 Google53±10*api price unknowncloud.google.com ↗Open ASR Leaderboard
18Distil-Whisper distil-large-v3.5 Hugging Face (Distil-Whisper)52±10*local~2.3GBhow to run › Open ASR Leaderboard
19Parakeet CTC 0.6B NVIDIA52±10*local~3.4GBhow to run › Open ASR Leaderboard
20Distil-Whisper distil-large-v3 Hugging Face (Distil-Whisper)51±10*local~2.3GBhow to run › Open ASR Leaderboard
21Parakeet TDT 1.1B NVIDIA50±10*local~5.8GBhow to run › Open ASR Leaderboard
22Parakeet RNNT 1.1B NVIDIA47±10*local~5.6GBhow to run › Open ASR Leaderboard
23STT En Conformer-CTC Large NVIDIA45±10*local~1.1GBhow to run › Open ASR Leaderboard
24Chirp Google43±10*comparison onlyOpen ASR Leaderboard
25STT En Conformer-Transducer Small NVIDIA34±10*local~0.6GBhow to run › Open ASR Leaderboard
26Distil-Whisper distil-large-v2 Hugging Face (Distil-Whisper)30±10*local~2.3GBhow to run › Open ASR Leaderboard
27STT En Conformer-CTC Small NVIDIA28±10*local~0.6GBhow to run › Open ASR Leaderboard
28STT En Conformer-Transducer Large NVIDIA27±10*local~1.1GBhow to run › Open ASR Leaderboard
29STT En FastConformer-CTC Large NVIDIA27±10*local~1.1GBhow to run › Open ASR Leaderboard
30STT En FastConformer-Transducer Large NVIDIA24±10*local~1.1GBhow to run › Open ASR Leaderboard
31Distil-Whisper distil-medium.en 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) Kyutainot yet calibratedlocal~6.7GBhow to run › Voxtral Realtime
—Voxtral Mini 4B Realtime (2602) Mistralnot yet calibratedapi $0.0060/audio min +local~3.2GBdocs.mistral.ai ↗Voxtral Realtime
—Voxtral Mini Transcribe V2 Mistralnot yet calibratedapi $0.0030/audio mindocs.mistral.ai ↗Voxtral Realtime

Includes 4 comparison-only models with no verified API or download · hide 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