MOSS Transcribe Diarize

MOSS Transcribe Diarize: Speaker Diarization & ASR

Transcribe conversations with speaker labels using MOSS Transcribe Diarize. Turn interview and meeting audio into readable, attributed segments.

2 credits / minuteYour credits work across all models.

Your output

A little input. A new possibility.

Your finished audio, image or text will appear here.

01 / Inside the model

Know what was said. See who said it.

MOSS Transcribe Diarize combines speech recognition with speaker diarization and time alignment. The official model produces speaker-labelled segments so a conversation is easier to follow than a single block of text. Upload a meeting excerpt, interview or discussion, then review the returned speaker and timing information. Labels distinguish voices within a recording; they do not establish a person’s real-world identity.

Speaker-labelled segments

Separate the voices in a conversation with consistent speaker labels.

Time-aligned speech

Use returned timestamps to navigate back to the relevant audio.

One transcription workflow

Process the recording without manually splitting every speaker turn.

02 / Examples & listening room

See it. Hear it. Get a feel for it.

Explore the official model

Official examples are credited to OpenMOSS. Studio samples were generated by us with the named API model. These are saved previews, not a result of your current settings. Research capabilities and available studio controls may differ.

A short voice recording

Studio input sample · English

Actual model transcription

[00:00.41 – 00:02.11] S01
What makes a good conversation?

[00:02.61 – 00:06.23] S02
A little curiosity, a little listening, and a question worth asking.

[00:06.68 – 00:08.32] S01
Then let us start with a question.

[00:08.68 – 00:10.45] S01
What would you like to create today?

Saved API output for this recording. Speaker labels describe voices, not verified identities.

03 / Use cases

Where it fits.

Interview review

Follow questions and answers in a recorded interview.

Meeting analysis

Find discussion segments for notes and follow-up work.

04 / Questions

A few things worth knowing.

What is speaker diarization?

It groups speech segments by detected voice, helping answer “who spoke when” without identifying the person by name.

How is Diarize priced?

2 credits per started minute. A 61-second recording costs 4 credits, based on server-verified duration.

Is it the same as plain transcription?

No. Plain Transcribe focuses on the words; Diarize adds speaker segmentation and time information when returned by the model.

Made for your next idea

Choose a model, add your input and review the credit cost. Successful results stay in your account history; AI output may be inaccurate.

Text is rounded up to a whole credit. Audio is billed per started minute. Live voice uses one credit per 6 seconds.

Failed tasks are refunded automatically.

Result links can expire. Download files you want to keep.

Model documentation