
专项更强用于部署 GPT-6 Astra、Sol、Luna 以及实时多模态智能体的企业级开发者平台与 API。

Descript is an AI-powered video and audio editor that lets you cut recordings by editing their transcript, then clean up, caption, translate and repurpose the result. Underlord, its AI co-editor, plus Studio Sound, voice cloning and screen recording turn a single tool into a full production pipeline for creators and teams.
| 维度 / 指标 | ![]() | ![]() |
|---|---|---|
| 官方域名 | apimodels.app | descript.com |
| 定价模式 | 付费 | 免费增值,付费 |
| 月访问量 | 4.5万 (45,042) | 326.78万 (3,267,817) |
| 月度环比流量变化 | +4837 (+12%) | +32.69万 (+11.1%) |
| 主要市场与份额 | 🇨🇳 中国 (49.7%) | 🇺🇸 美国 (38.9%) |
| 直接访问 / 月 | 1.95万 | 164.94万 |
| 用户评分 | 3.6 | 4.6 |
| 支持的平台 | 网站 | 网站 |

一个 API Key 调用 165+ 图像、视频、音频与 LLM 模型,价格最高低于官方 95%
一个 API Key 与 base URL 即可访问多厂商的图像、视频、LLM 与语音模型,切换模型只需改动一个模型名字符串。
把 base_url 指向平台即可复用现有 SDK 代码、Agent 框架与 IDE 助手,对话与 messages 接口形状与官方一致。
仅对返回结果的请求扣费,没有月费、没有会过期的门槛额度,失败生成不收费。
热门模型背后有多个上游通道,主通道报错、限流或超时时自动在备用通道重试。

Descript is an AI-powered video and audio editor that lets you cut recordings by editing their transcript, then clean up, caption, translate and repurpose the result. Underlord, its AI co-editor, plus Studio Sound, voice cloning and screen recording turn a single tool into a full production pipeline for creators and teams.
Edit audio and video by deleting, rearranging or retyping words in the automatic transcript, with a full multitrack timeline available when you need it.
Describe the edit you want in plain language and let the AI assistant assemble a tight cut, add clips and handle repetitive production work.
Remove background noise, level out voices, and fix misread lines with Regenerate Speech using a clone of your own voice.
Generate subtitles and transcripts in a click, translate video into other languages, and reformat long recordings into shareable vertical clips.

专项更强用于部署 GPT-6 Astra、Sol、Luna 以及实时多模态智能体的企业级开发者平台与 API。
专项更强Provides industry-leading voice cloning and text-to-speech generation, but does not offer media recording or timeline editing.
专项更强Provides industry-leading voice cloning and text-to-speech generation, but does not offer media recording or timeline editing.
Focuses on text-to-video generation and agentic editing, whereas Descript centers on editing recorded audio and video.

Offers robust online collaborative video editing and AI tools, but lacks deep script-based transcript manipulation.

专项更强Provides highly accurate transcription and translation across numerous languages, but lacks creative video editing suites.
专项更强Provides highly accurate transcription and translation across numerous languages, but lacks creative video editing suites.

一个 API 接入 1500+ 生产级生成式媒体模型

专项更强Specializes in automatically slicing long-form video into viral short clips, but lacks full podcast production depth.
专项更强Specializes in automatically slicing long-form video into viral short clips, but lacks full podcast production depth.