#1
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.
| 面向/指標 | ![]() | ![]() |
|---|---|---|
| 官方網域 | apimodels.app | descript.com |
| 定價模式 | 付費 | 免費增值、付費 |
| 每月造訪次數 | 4.5萬 (45,042) | 326.78萬 (3,267,817) |
| 月流量變化量 | +4837 (+12%) |
| +32.69萬 (+11.1%) |
| 主要市場與市佔 | 🇨🇳 中國 (49.7%) | 🇺🇸 美國 (38.9%) |
|---|
| 每月直接造訪 | 1.95萬 | 164.94萬 |
|---|
| 使用者評分 | 3.6 | 4.6 |
|---|
| 支援平台 | 網站 | 網站 |
|---|

一組 API Key 呼叫 165+ 圖像、影片、音訊與 LLM 模型,價格最高低於官方 95%
一組 API Key 與 base URL 即可存取多廠商的圖像、影片、LLM 與語音模型,切換模型只需改動一個模型名字串。
把 base_url 指向平台即可沿用既有 SDK 程式碼、Agent 框架與 IDE 助手,對話與 messages 介面形狀與官方一致。
僅對回傳結果的請求扣費,沒有月費、沒有會過期的門檻額度,失敗生成不收費。
熱門模型背後有多個上游通道,主通道錯誤、限流或逾時時自動在備用通道重試。

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.
#1專項更強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.

專項更強Provides highly accurate transcription and translation across numerous languages, but lacks creative video editing suites.

一個 API 串接 1500+ 可上線的生成式媒體模型

專項更強Specializes in automatically slicing long-form video into viral short clips, but lacks full podcast production depth.
專項更強Provides industry-leading voice cloning and text-to-speech generation, but does not offer media recording or timeline editing.
提供強大的瀏覽器影片編輯與自動字幕功能,但缺乏 Descript 的文件式文字編輯模式。
專項更強Provides highly accurate transcription and translation across numerous languages, but lacks creative video editing suites.
專項更強Specializes in automatically slicing long-form video into viral short clips, but lacks full podcast production depth.