A model for every use.

State-of-the-art multilingual speech recognition across 52 languages & dialects

NVIDIA's multilingual speed flagship — 25 European languages, TDT transducer with native word timestamps

FireRedTeam's Mandarin-first bilingual ASR — attention encoder-decoder tuned for state-of-the-art Chinese and dialect accuracy

Bilingual Chinese + English streaming speech recognition — a compact icefall Zipformer2 transducer

Chinese multi-dialect speech recognition -- a WeNet E-Branchformer (CTC + attention) tuned for Sichuan and 22 regional dialects

Multilingual speech recognition across 52 languages & dialects — the fast, lightweight Qwen3-ASR

Fast multilingual speech recognition from FunAudioLLM — non-autoregressive SenseVoice, tuned for Chinese, Cantonese, English, Japanese and Korean

FireRedTeam's LLM-backbone Mandarin-first bilingual ASR — 8B+ parameters engineered for state-of-the-art Chinese and dialect accuracy

Xiaomi MiMo's end-to-end 8B speech model — state-of-the-art Mandarin, English, and Cantonese recognition, fully on-device

Joint transcription and speaker diarization in a single 0.9B-parameter model — know who said what, and when

Multilingual speech recognition across 40 languages, base tier -- a compact 140M WeNet/ESPnet E-Branchformer (CTC + attention)

Chinese multi-dialect speech recognition, base tier -- a compact 140M WeNet E-Branchformer (CTC + attention) for Sichuan and 22 regional dialects

Multilingual speech recognition across 40 languages -- a WeNet/ESPnet E-Branchformer (CTC + attention) covering South/Southeast/Central Asian and Chinese-dialect speech

Dedicated 2B ASR for 14-language transcription

Compact bilingual speech recognition — Mandarin and English in an ~0.8B SAN-M + Qwen3 pack

IBM Granite Speech 4.1 — a 2B multilingual ASR model with strong English accuracy

Tiny 27M-parameter English ASR built for real-time, on-device transcription

Fast multilingual Whisper built from pruned large-v3

OpenAI's most accurate Whisper, the v3 large checkpoint

Compact multilingual Whisper, a step up from tiny

Compact English-only Whisper for fast English transcription

High-accuracy multilingual Whisper at 769M parameters

High-accuracy English-only Whisper at 769M parameters

Compact multilingual Whisper for local transcription

Balanced English-only Whisper for accurate local transcription

The smallest multilingual Whisper for fast local transcription

The smallest English-only Whisper, fastest for English speech