SSyncDev

Automatic speech recognition AI Models

Models listed

75

Published in this category

Worth weighing up

What goes in and out, licence terms, and whether you can host it yourself

How we treat data

Published specs only — we don't estimate numbers a vendor hasn't stated

Automatic speech recognition models are a source-backed task collection in this directory. The current editorial inventory contains 68 mapped model records. Task membership is a discovery signal, not a performance ranking, deployment recommendation, or proof that every checkpoint accepts the same inputs and returns the same outputs.

Start with the model list, then open each record that matches your data, operating constraints, and intended workflow. Check the primary source, documented modalities, license, release information, and implementation notes before using a model in production.

This collection keeps unsupported pricing, availability, and benchmark claims blank. Each page remains outside the public index until an editor approves its content and related model records.

Automatic speech recognition model list

Scan the table below, then open any model for pricing, limits and the full write-up.

75 models
Qwen-Audio-3.1-Realtime Flash
Alibaba
45.1262.14K———
Hy-SimulMT-30B-A3B
Tencent
9.9————
Ming-3.0-audio-flash
inclusionAI
14.8————
Ming-3.0-asr-tiny
inclusionAI
9.8————
MAI-Transcribe-2-Streaming
Microsoft
—————
Grok Voice Transcribe 2.0
xAI
—————
Gemini 3.5 Transcribe Live
Google
—————
Grok Voice STT 1.0
xAI
—15K———
GPT Realtime Whisper
OpenAI
9.516K———
Whisper 3 Large
OpenAI
7.9448$0.00$0.00—
Whisper Large v3 Turbo
OpenAI
6.3448———
Gemini 1.5 Pro
Google
63.62M$1.25$5.0065 t/s
Cohere Transcribe Arabic
Cohere
5.0————
StepAudio 3 ASR Max
StepFun
5.0————
MAI-Transcribe-2
Microsoft
—————
Muse Voice Transcribe 1.0
Meta
—————
Scribe v3
ElevenLabs
15.0————
Scribe v3 Live
ElevenLabs
10.0————
Universal-3.6 Pro
assemblyai
9.7————
Transcribe 1 Pro
fish-audio
14.7————
Scribe v2 Medical
ElevenLabs
14.6————
openai/whisper-large-v3-turbo
openai
6.3————
openai/whisper-large-v3
openai
6.6—$0.00$0.00—
airesearch/wav2vec2-large-xlsr-53-th
airesearch
5.0————
anuragshas/wav2vec2-large-xlsr-53-telugu
anuragshas
5.0————
argmaxinc/whisperkit-coreml
argmaxinc
5.0————
CohereLabs/cohere-transcribe-03-2026
CohereLabs
5.0————
comodoro/wav2vec2-xls-r-300m-cs-250
comodoro
5.0————
distil-whisper/distil-large-v3
distil-whisper
5.0————
facebook/wav2vec2-base-960h
facebook
5.0————
gigant/romanian-wav2vec2
gigant
5.0————
Granite Speech 5.0 TurboCTC
IBM Granite
5.0————
handy-computer/cohere-transcribe-03-2026-gguf
handy-computer
5.0————
handy-computer/nemotron-3.5-asr-streaming-0.6b-gguf
handy-computer
5.0————
handy-computer/parakeet-unified-en-0.6b-gguf
handy-computer
5.0————
Harveenchadha/vakyansh-wav2vec2-tamil-tam-250
Harveenchadha
5.0————
imvladikon/wav2vec2-xls-r-300m-hebrew
imvladikon
5.0————
indonesian-nlp/wav2vec2-indonesian-javanese-sundanese
indonesian-nlp
5.0————
jonatasgrosman/wav2vec2-large-xlsr-53-arabic
jonatasgrosman
5.0————
jonatasgrosman/wav2vec2-large-xlsr-53-chinese-zh-cn
jonatasgrosman
5.0————
jonatasgrosman/wav2vec2-large-xlsr-53-dutch
jonatasgrosman
5.0————
jonatasgrosman/wav2vec2-large-xlsr-53-greek
jonatasgrosman
5.0————
jonatasgrosman/wav2vec2-large-xlsr-53-hungarian
jonatasgrosman
5.0————
jonatasgrosman/wav2vec2-large-xlsr-53-japanese
jonatasgrosman
5.0————
jonatasgrosman/wav2vec2-large-xlsr-53-persian
jonatasgrosman
5.0————
jonatasgrosman/wav2vec2-large-xlsr-53-polish
jonatasgrosman
5.0————
jonatasgrosman/wav2vec2-large-xlsr-53-portuguese
jonatasgrosman
5.0————
jonatasgrosman/wav2vec2-large-xlsr-53-russian
jonatasgrosman
5.0————
KBLab/wav2vec2-large-voxrex-swedish
KBLab
5.0————
Khalsuu/filipino-wav2vec2-l-xls-r-300m-official
Khalsuu
5.0————
kingabzpro/wav2vec2-large-xls-r-300m-Urdu
kingabzpro
5.0————
MahmoudAshraf/mms-300m-1130-forced-aligner
MahmoudAshraf
5.0————
mesolitica/wav2vec2-xls-r-300m-mixed
mesolitica
5.0————
mistralai/Voxtral-Mini-4B-Realtime-2602
mistralai
5.0————
mlx-community/parakeet-tdt-0.6b-v2
mlx-community
5.0————
mlx-community/parakeet-tdt-0.6b-v3
mlx-community
5.0————
nvidia/nemotron-3.5-asr-streaming-0.6b
NVIDIA Research
5.0————
nvidia/parakeet-ctc-1.1b
NVIDIA Research
5.0————
openai/whisper-base
openai
5.0————
openai/whisper-small
openai
5.0————

1–60 of 75 models · select a column to sort

About this order: Recommended shows our editorial shortlist first, followed by recent releases. The spec score is a 0–100 figure SyncDev calculates from each vendor's published specifications — context window, reasoning support, input modalities, tool calling, maximum output and how recently the model shipped. It measures breadth of capability, not benchmark performance, so a higher-scoring model is not automatically the better choice for your task.

Automatic speech recognition model questions

It groups source-backed directory records for research and comparison. Review each model page and its primary documentation because collection membership alone does not prove quality, availability, or suitability.

All AI models →