Cohere Transcribe Arabic

Cohere · 2026 · Speech Recognition · Canada

A to Z

A · App: No
B · Built By: Cohere
C · CEO & Politics: Aidan Gomez — Canadian centrist / open-source advocate
D · Date: 2026
E · Expertise: Intermediate+
F · Free Tier: Yes
G · Generates: Text only
H · Deployment: Open weights (Hugging Face; Apache 2.0); day-0 mlx-audio support
I · Inputs: Text
J · Jurisdiction: Canada
K · Key Staffers: Aidan Gomez (CEO & Co-Founder, original Transformer co-author), Ivan Zhang (Co-Founder)
L · Languages: English-primary
M · Model Type: Speech Recognition
N · Safety Issues: None reported
O · Open Source: Yes — open weights
P · Pricing: Free (open weights, Apache 2.0 license)
Q · AIDb Rating: 7/10 · AIDb v2.0 (curated): Capability 7/10 · Currency 10/10 · Access 8/10 · Significance 5/10 → 7.45
R · What Makes It Special: 2B-parameter Apache 2.0 Arabic speech-to-text: leads the Hugging Face Arabic ASR leaderboard at 25.87 WER (~11 points better than Whisper Large V3), with ~96% human preference head-to-head; handles dialect variety, code-switching, and Arabic-English bilingual speech.
S · Stock / Status: Private (~$20B combined valuation in Sep 2026 merger agreement with Aleph Alpha)
T · Training Cutoff: [UNKNOWN]
U · Users: [UNKNOWN]
V · Voice Chat: No
W · Weights: Downloadable
X · X Handle: @cohere
Y · Year Founded: [UNKNOWN]
Z · Bottom Line: Open-weights Speech Recognition from Cohere, released 2026.

Data completeness 88% · Last verified 2026-08-09 · Primary source ↗

“Cohere Transcribe Arabic.” AIDb — The AI Database. Verified 2026-08-09. https://theaidatabase.com/m/cohere-transcribe-arabic.html