Patient consultations, assessment interviews and recorded conversations, transcribed.

Conversation & interview is the mode for recordings with several speakers, including patient consultations, psychiatric assessment interviews and interviews with relatives. Tippiti identifies the speakers, corrects misheard medical terminology and medication names even mid-conversation, and delivers a full verbatim transcript, a clean verbatim transcript or a summary. If requested, audible behavioural observations such as [laughs] or [cries] are noted directly in the transcript. If the recording contains a dictated passage, Tippiti recognises the switch.

Transcript · Excerpt validated
Doctor The sociopathy[TOOLTIP] Context matters when two clinical terms sound similar. “Sociopathy” is a real clinical term, correctly spelt, but it means something quite different from the “social phobia” that was actually said.

Tippiti works on the transcript as a whole and resolves passages like this from context. [/TOOLTIP] social phobia, erm, when was that diagnosed?
Patient Yes, well … that was 2020. Er, at the day clinic.

To turn an assessment interview into a case history and interview section for the report, use Assessment interview & case history.

Try Tippiti

No sign-up

Upload test dictation

Upload your own dictation and see the result within minutes. No registration required.

Upload test dictation now 20,000 characters free

Create free account

Get 20,000 characters free, with no payment details and no subscription.

Create free account
Questions? Get in touch support@tippiti.io
The options

You decide how your transcript is produced.

For each recording, choose how it is processed when you upload it. The following options are available.

Speaker labelling

Roles instead of numbers

Tippiti marks every change of speaker and labels identifiable roles instead of using only Speaker 1 and Speaker 2. You can also switch off speaker separation and receive continuous text in paragraphs.

Transcript style

Full verbatim, clean verbatim or summary

A full verbatim transcript keeps slips of the tongue and filler words. Clean verbatim removes only the ums, ers and false starts and leaves the wording unchanged. A summary reduces the conversation to its key statements while retaining speaker attribution and order.

Timestamps & behavioural observations

Additional options

If needed, Tippiti marks changes of speaker with timestamps. Audible observations such as [laughs] or [cries] are noted directly in the transcript. Both options can be enabled independently.

When you upload a file, you can attach your own instructions, for instance a note about anything unusual in the recording or about the way you work.

Two kinds of text

Dictated passages within a conversation, recognised and written up.

During an assessment interview, the assessor asks questions and the person being assessed responds. If the recording also contains a dictated finding or an instruction to the typist, Tippiti recognises the switch and processes the passage accordingly.

The two types of content are handled separately. The conversation remains a transcript, while the dictated passage is rendered as clean text, with dictation commands executed, dictated spellings incorporated and remarks to the typist removed, exactly as in Dictation mode.

The same applies in reverse. If the patient says “you can delete that”, it is conversation content and stays in the transcript. Whether a passage is dictation or conversation is decided by speaker role and context, not by the wording alone.

Assessment interview · Excerpt dictation recognised
Assessor
What does your daily routine look like?
Examinee
I get up around nine and do nothing at all at first.
Assessor
The examinee reports comma she gets up around nine and does nothing at all at first full stop Dictation · written up
The examinee reports that she gets up around nine and does nothing at all at first.
Examinee
You can delete that. Conversation content: stays in the transcript
Who it’s for

How medico-legal experts, doctors and transcription services use this mode

Assessors: verbatim transcript

If you need a verbatim transcript of an assessment interview for the file or for cross-checking, this mode delivers it with speaker attribution. If you need a case history and interview section in a fixed outline, Assessment interview & case history is the right mode.

Go to Assessment interview & case history

Physicians: patient consultations

History-taking conversations and informed-consent discussions are documented without any typing afterwards, either as a speaker-labelled transcript or as a concise summary of the key statements, whichever belongs in your records.

Go to the use cases

Transcription services: interview assignments

Verbatim transcripts, interviews and recorded meetings, including non-medical assignments. With the conversation mode you can take on such assignments without hours of manual transcription.

More on the transcription services page
Pricing

What Conversation & interview costs.

An hour-long conversation includes pauses, hesitation and silence. With per-minute pricing, that time is billed as well. Tippiti charges for the characters of the finished transcript, at €0.50 per 1,000 characters, the same as in Dictation mode.

A summary therefore costs less than a verbatim transcript, because less text is produced. A verbatim transcript of 40,000 characters costs €20.00, a concise summary of the same recording only a fraction of that. You pay for the result you actually use.

The price includes the entire quality process. The transcript is corrected, checked for spelling accuracy and plausibility, and finally compared against the original recording. How this process works in detail is described on the Why Tippiti page.

All mode prices at a glance
€0.50 per 1,000 characters
Speaker labelling by role included
All transcript styles at the same price
Optional timestamps
Optional behavioural observations
No base fee, no minimum term
Try it free now
You get 20,000 characters free to try it out
Good to know

Frequently asked questions about Conversation & interview

Can Tippiti create a conversation transcript automatically?

Yes. Tippiti can turn a recording with several speakers into a finished transcript automatically. In Conversation & interview mode, you choose between full verbatim, clean verbatim and summarised output. You can also enable speaker labelling, timestamps and behavioural observations.

How does Tippiti recognise who is speaking?

Tippiti distinguishes speakers from their voices and the context of the conversation, then assigns each turn to the appropriate speaker. Where a role can be identified reliably, it uses labels such as [Doctor], [Patient] or [Assessor]. Otherwise, it uses numbered labels such as [Speaker 1] and [Speaker 2]. For long recordings, Tippiti keeps these assignments consistent across section boundaries.

What happens to filler words and slips of the tongue?

That is determined by the chosen transcript style:

  • Full verbatim preserves filler sounds, repetitions and unfinished sentences. Nothing is cleaned up.
  • Clean verbatim removes speech disfluencies such as “um” and false starts, while the wording itself is preserved in full.
  • Summarised conveys the key statements in concise sentences, while keeping the speaker assignment and order.

A summary is deliberately shorter. If every detail must be preserved, full verbatim is the right choice.

How many speakers can a recording have?

There is no fixed limit. Tippiti processes two-person conversations just as well as recordings with several participants, for example a patient consultation with relatives or a team case discussion.

With speaker labelling enabled, each speaker receives a label. Without speaker labelling, continuous text without speaker separation is produced.

When should I use Conversation & interview, and when Assessment interview & case history?

Conversation & interview produces a full verbatim or clean verbatim transcript, or a summary of the conversation. If you need a structured case history and interview section for a medico-legal report instead, Assessment interview & case history is the appropriate mode.

Depending on your purpose, either mode may be suitable for the same recording: Conversation & interview for a transcript, or Assessment interview & case history for a report section written up from the recording.

Can I dictate in the middle of a conversation?

Yes. This is a core feature of the mode. If you begin dictating a paragraph for the clinical findings or a report during the conversation, Tippiti recognises the change and converts the passage into polished dictated text.

Tippiti does not treat remarks made by other participants as dictation commands. If a patient says “you can delete that”, the remark remains part of the conversation transcript.

How do the timestamps work?

If you enable timestamps, every change of speaker is marked with a time in the format [mm:ss]. Each timestamp shows the time elapsed since the start of the recording.

This lets you locate individual passages in the recording quickly.

Can Tippiti record audible behavioural observations?

Yes. When behavioural observations are enabled, Tippiti notes audible non-verbal events such as [laughs] or [cries] directly in the transcript.

What does transcribing a conversation cost?

Transcribing a conversation costs €0.50 per 1,000 characters of the finished transcript. That is the same price as in the dictation mode, regardless of the options chosen.

A one-hour conversation often produces a verbatim transcript of 40,000 to 60,000 characters, depending on how much is said. This costs approximately €20 to €30. A summary is considerably shorter and therefore costs less. Pauses and silence in the recording are not charged.

See the pricing overview for more examples.

See more frequently asked questions and answers

See for yourself.

Upload a test dictation and see what Tippiti makes of your recording. Try it free with no registration and no commitment.

Create account
Questions? Get in touch support@tippiti.io

Loading…