Transcription

Turn speech into usable text inside the same audio workflow.

Transcription is now presented honestly as a production support lane connected to captions, dubbing, and review, not as a fake standalone model catalog.

Transcript output

Speaker splitsReview-friendly
TimecodeDownstream ready
Caption handoffAdjacent
WorkspaceAudio and AI lanes

The emphasis here is workflow correctness: transcription should feed the rest of production instead of pretending to be a separate product.

Waveform Voice Lane

Keep the page calm, signal-rich, and audio-first. Voice routes should feel cleaner and more controlled than visual generation lanes while still pointing clearly into execution.

Voice signals

3

Linked lanes

3

Voice uses

3

Action surfaces

4

Workflow

Transcription should feed the rest of the system.

Caption and script adjacency

Transcribed content can stay close to captioning, prompt, and review flows already present in the platform.

Review-oriented output

The result is positioned for editorial and producer review rather than a raw dump of text.

No fake model claims

This page now avoids inventing a dedicated transcription model stack that the current public registry does not expose.

Connected Workflow

The current transcription lane is defined by these adjacent platform surfaces.

Audio Studio

Speech sources, cleaned takes, and generated narration already live here before transcription is requested.

Workspace

Caption Support

AI Caption with integrated billing and provider guardrails.

2 credits · Free+ · Gemini

Queue and publish

Transcript-driven outputs can continue into review, subtitle packaging, and final delivery.

Operations

Use Cases

Where transcription belongs.

Interview review

Give editorial and production teams searchable spoken content without leaving the main workflow.

Editorial

Subtitle prep

Prepare caption-ready text that can move into localization or publish packaging.

Video

Audio library indexing

Keep spoken material easier to search and reuse in later productions.

Library

Keep spoken text attached to the rest of production.

Use the audio and caption lanes together when speech needs to become reviewable text.

Open Audio Workspace