Model Cadence
Plus $4/mo

GLM-ASR-2512

Z.ai · Released Dec 10, 2025 · Closed weights

Speech recognition model for multilingual and dialect transcription with custom hotwords

Lab announcement ↗Open in the timeline
BENCHMARKS

Not in the Epoch Capabilities Index. Epoch benchmarks what it can run, so this is a gap in coverage, not a poor result.

Z.ai's past year

12 release days in the past year, about one every 30 days. The next is expected around Nov 18, 2026. Forecasts ↗

NovDecJanFebMarAprMayJunJulAugSepOctNov

Specifications

RELEASE DATEDec 10, 2025
WEIGHTSClosed weights
CONTEXT WINDOWNot listed
MAX OUTPUT0
REASONINGNot listed
TOOL CALLINGNot listed
INPUTSaudio/wav, audio/mpeg
OUTPUTStext

Models.dev record ↗

Specifications and prices from Models.dev; availability and limits may differ by provider. Benchmarks from Epoch AI (CC BY 4.0), LiveBench and the other sources named above.