What is YobiYoba and what does it do?

YobiYoba is a speech recognition service that transcribes audio and video recordings into time-coded text. You upload a file, specify the language, and the service converts the speech into an editable transcript that stays synchronized with the audio. It suits anyone who needs a written record of a recording — interviews, meetings, lectures, subtitles — without typing it out manually. Registration is free, and transcription is billed on a pay-as-you-go basis.

What YobiYoba actually produces

The output is not just a plain block of text. According to the service, processing yields a fully annotated document containing:

• Speech and non-speech segments
• Speaker labels
• Words with time codes
• Confidence scores
• Punctuation marks

Internally the result is an XML document, which is then converted on demand into the format you want.

The 4-step process

YobiYoba describes its workflow as four steps:

1. Upload your file(s) — audio or video files in any format, from any source.
2. Specify the language and process the file(s) — you can also supply textual information about your data to help the automatic processing.
3. Verify & edit the transcripts — transcripts are synchronized with the audio so you can check and modify them.
4. Download transcripts — choose from a range of output formats.

Supported output formats

You can export transcriptions in a wide selection of text and subtitling formats, including:

How the recognition works

The process runs in three stages:

1. The software identifies the audio segments that contain speech.
2. It recognizes the language being spoken — if it wasn't already known and specified in advance.
3. It converts the speech segments into time-coded text.

One point the service states plainly: like any pattern recognition technology, speech transcription cannot be error-free. That is why an editing step is built into the workflow rather than treated as optional.

Pricing model

YobiYoba uses a simple pay-as-you-go scheme:

• From 0.01 € (excl. tax) per minute, ranging from 0.08 € to 0.01 € per minute depending on volume (degressive pricing).
• No minimum fee per file.
• Transcription credit never expires.
• You pay only for the amount of transcribed speech, not for the file duration.
• No extra fee to manage, edit, or convert transcripts.
• All prices include EU VAT.
• You can top up your account with PayPal, credit card, or a coupon.

When YobiYoba is a good fit

Choose it if you want per-minute billing with no subscription commitment, need time-coded output for subtitles or timestamped notes, and are comfortable reviewing and correcting the automatic transcript afterward. Because you're only charged for actual speech rather than total file length, recordings with long silences or non-speech sections cost less than their runtime might suggest.

If you need a fully hands-off result with no editing step, keep in mind that the service itself flags transcription as inherently imperfect — budget time for the verify-and-edit stage.