Z.aiGLM Speech
GLM-ASR-2512
A hosted recognizer for multilingual audio transcription.
Practical use
Practical guidance. Split recordings with overlap at meaningful speech boundaries. Check that names from the custom dictionary are transcribed correctly without causing similar ordinary words to be replaced.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | API |
| Model identifiers | glm-asr-2512 |
| Upload limits | At most 30 seconds and 25 MB per file.GLM-ASR-2512 official documentation |
| Features | Streaming output and a custom vocabulary dictionary.GLM-ASR-2512 official documentation |
| Languages | Chinese varieties, English and other listed languages.GLM-ASR-2512 official documentation |
Related models
- GLM-ASR-Nano-2512
Z.ai · GLM Speech
A 1.5-billion-parameter downloadable speech recognizer.
Launch date not confirmedDownloadable A two-stage speech system with voice cloning and streaming inference.
Launch date not confirmedDownloadable