Subtitling workflow

From raw audio to translated, timed subtitles in a single bundled pipeline.

What it chains

The Subtitling workflow runs three services back to back:

Transcription — speech-to-text from your audio.
Forced alignment — precise word- and segment-level timings.
Translation — translated subtitles in your target language.

You upload audio once; the bundle produces timed, translated subtitles at the end.

Transcript review

You can opt to pause after transcription to review and correct the transcript before alignment and translation proceed. Catching recognition errors here keeps the timings and the translation clean.

Pricing & refunds

The bundle is priced upfront per minute of audio, in two tiers:

Standard — all three stages.
Premium — adds AI refinement on the translation stage.

Refund-on-failure protection

You’re charged upfront on the estimated duration, but any stage that fails is refunded. Bundles also auto-expire after 30 days with an automatic refund if not completed.

See pricing for current per-minute rates, and the workflows overview for how bundles compare.

Related bundles

Don’t need every stage? Two lighter bundles are on the way:

Subtitle Base — transcription + alignment (no translation).
Quick Translate — transcription + translation (no alignment).

Coming soon

These bundles aren’t live yet. For now, combine the standalone services or use the full Subtitling workflow.

Via the API

Create subtitling pipelines programmatically with an API key and presigned uploads. Track progress with webhooks. See the API reference for the workflow endpoints.