Speech to Text

Turn audio into editable, searchable text

Upload audio, choose recognition languages, and create transcripts for creator, education, and business workflows.

Open the transcription workflow

Multilingual recognition

Handle Chinese, English, and mixed-language audio for meetings and media.

Transcript history

Signed-in users can review history and copy transcript text from the workspace.

API ready

Submit ASR tasks through Open API and integrate transcription into your product.

Where transcription fits

Creator

Podcast and short-video notes

Turn long audio into text drafts for editing, summaries, titles, and republishing.

Team

Meeting and course records

Convert recordings into searchable text and reduce manual note cleanup.

API

In-product captions

Submit audio through API workflows to generate captions and transcript results.

From audio to text

1

Upload audio or call the API

Choose an audio file in the workspace or submit an accessible audio URL.

2

Select languages and create a task

Use Chinese, English, or multilingual recognition depending on the material.

3

Copy, download, or continue

Use completed transcripts for editing, captions, summaries, and archives.