Podcast transcription

How does it work ?

Our platform uses the OpenAI "Whisper" model to automatically create transcripts from podcast audio.

Machine learning technology applies neural network models to audio content to detect speech and convert it into text.

Models are trained to understand a specific language and dialect. Some language have much better training sets available, and so produces much better accuracy. Accuracy is typically measured in "word error rate" (WER), where a WER of 5-10% is considered to be good quality, 20% is acceptable and 30% or more deliver relatively poort quality.

The top-performing languages for Whisper transcription accuracy are English, Italian, German, and Spanish. Mid-performing languages include French, Portuguese, and Japanese, while the worst-performing languages are Arabic and Hindi.

See this article for more details.

Why use it ?

Attach a transcript to make subtitles available to your audience, a great accessibility feature.

We also include the transcript in our web page metadata for episodes when it is available to boost SEO.

Using transcription

Customers on our "Pro" podcast package or higher can enable this feature on their publisher's billing portal. Once activated for an account, admin users can:

• Manually trigger automated transcripts for individual episodes or,
• Enable auto transcription on a show (channel) to automatically transcribe all new episodes published to it.

Managing transcripts

Once a transcript is available on an episode it will be included in RSS feeds as part of the Podcast 2.0 standard.

Customers can also choose to make this directly visible to end users on episode web pages.

Transcripts can also be manually uploaded for each episode, we support importing SRT or VTT transcript files.

Use the "Transcript" section of the admin panel on episodes to view, download, create or change it's transcript.

Transcription billing

Automated transcription is invoiced per audio minute processed at an hourly rate.

Amounts are invoiced at the end of a calendar month in arrears based on the amount of minutes processed. For up-to-date pricing, please see our podcast pricing page.