Model details

GLM-ASR-2512

GLM · glm-asr-2512

GLM-ASR-2512 is Zhipu GLM's new-generation speech recognition model, supporting real-time conversion of speech into high-quality text. Whether in daily chats, meeting minutes, work documents, or scenarios containing specialized terminology, it can accurately recognize and convert speech, significantly improving input and recording efficiency. The model still maintains industry-strong recognition performance across multiple scenarios and accents, with a character error rate (CER) of only 0.0717, providing a fast and reliable voice input experience.

中转最低95% of official¥15.20 / ¥15.20
2家在卖

The best way to buy GLM-ASR-2512

The best deal for each of three ways to buy. Tap a card to see every option of that kind.

Pay-as-you-go API · relay stationsFor coding and tools like Cursor and Claude Code
For using the web app and mobile app, no coding
Official subscriptionsFor a genuine official plan in your own name

GLM-ASR-2512

GLM-ASR-2512 is Zhipu GLM's new-generation speech recognition model, supporting real-time conversion of speech into high-quality text. Whether in daily chats, meeting minutes, work documents, or scenarios containing specialized terminology, it can accurately recognize and convert speech, significantly improving input and recording efficiency. The model still maintains industry-strong recognition performance across multiple scenarios and accents, with a character error rate (CER) of only 0.0717, providing a fast and reliable voice input experience.

View intro source
Official price · Input¥16.00
Sellers2 家

The best way to buy GLM-ASR-2512

The best deal for each of three ways to buy. Tap a card to see every option of that kind.

Pay-as-you-go API · relay stationsFor coding and tools like Cursor and Claude Code
For using the web app and mobile app, no coding
Official subscriptionsFor a genuine official plan in your own name
No reviews yet — write the first oneSee reviews ↓

模型介绍

GLM-ASR-2512 is Zhipu GLM's new-generation speech recognition model, supporting real-time conversion of speech into high-quality text. Whether in daily chats, meeting minutes, work documents, or scenarios containing specialized terminology, it can accurately recognize and convert speech, significantly improving input and recording efficiency. The model still maintains industry-strong recognition performance across multiple scenarios and accents, with a character error rate (CER) of only 0.0717, providing a fast and reliable voice input experience.

模型基础信息

厂商
智谱 GLM
模型类型
语音转写
能接收什么
音频可以发给它的内容类型
能产出什么
文本它能生成的内容类型
能听音频吗
可以
怎么计费
按 Token 计费官方按什么单位收钱
现在还能用吗
状态待核实暂未收录当前可用状态,请查看官方说明。
这些资料是哪个地区的资料适用地区
中国大陆厂商专门为中国大陆公布的资料。
它会做什么能处理音频会把语音转成文字

官方价格

折扣与价格评分按中国大陆的官方价计算

计价项适用范围官方价格
输入中国大陆16 CNY每百万 Token
它还叫这些名字(3 条)
glm-asr-2512glm-asr智谱 GLM asr 2512

不同地方写法可能不一样,列在这里方便你对上号。名字太模糊、认不准的不会公开。

User reviews

No reviews yet. If you have used it, share the first honest review and help others avoid pitfalls.

Review this model

Rating
Optional
编辑器加载中…