Interview Transcript to Audio, With a Voice for Each Speaker

Free to sign up, no card. Creating uses credits.

Paste a Q&A or upload a transcript. FullCastBook works out which lines are questions and which are answers, gives the interviewer and every guest a different AI voice, and returns the whole interview as one audio file.

Who it's for
  • Written Q&A as an episode
  • Research and stakeholder playback
  • Translated interviews
Alice's Adventures in Wonderland — The Cheshire Cat
NarratorNaomiAliceAbbyCheshire CatSnik How it works
Alice's Adventures in Wonderland cover

Lewis Carroll

Alice's Adventures in Wonderland

Alice asks the grinning Cheshire Cat for directions — and gets none.

The Cat only grinned when it saw Alice. It looked good-natured, she thought; still it had very long claws and a great many teeth, so she felt it ought to be treated with respect.

Cheshire Puss, would you tell me, please, which way I ought to go from here?

Cheshire CatSnikSly

That depends a good deal on where you want to get to.

I don't much care where—

Cheshire CatSnikSly

Then it doesn't matter which way you go.

—so long as I get somewhere.

Cheshire CatSnikSly

Oh, you're sure to do that, if you only walk long enough.

~1 min · 3 voices · ready to play7
Free preview, no signup to listen. Your own chapters & export need an account and credits.I'm ready →
AI voices to cast
137
70 standard · 67 premium
file types in
5
EPUB · PDF · DOCX · TXT · MD
ways out
3
M4B with chapters · MP3 · ZIP
voice models
4
Gemini · ElevenLabs

Step-by-step guide

How to use Interview Transcript to Audio

No card to sign up, nothing to install.

  1. Add the transcript

    Paste the interview or upload it as a DOCX, PDF, TXT or MD file. Labels like "Interviewer:" and "Ruth:" before each turn give the cleanest result.
  2. Check the speakers

    Each turn is assigned to the interviewer or a guest, and any intro text goes to the narrator. Reassign a line in one click if it landed on the wrong person.
  3. Choose two contrasting voices

    Pick a voice for the interviewer and one for each guest, clearly different in pitch or age, and add notes like [laugh] or [thoughtful] where the transcript calls for them.
  4. Export the episode

    Listen, regenerate any line that sounds off, and download one MP3. A long interview split into topics can go out as an M4B with chapter marks.

Hear an example

Hear an interview transcript voiced in FullCastBook

Generated from the script below with the studio's own voices and settings, one voice per speaker, joined the way an export joins lines. No edits afterwards.

Twenty-two years of rooftop bees

Interviewer · Ruth · Voices: Gemini 3.8 Flash TTS

0:00 / 0:58
  1. InterviewerRuth, you've kept bees on this rooftop for twenty-two years. How did it start?Iapetus · warm, curious
  2. Ruth[laugh] By accident. A swarm landed on my fire escape, and nobody else would deal with it.Gacrux · amused, fond
  3. InterviewerSo you just picked them up?Iapetus · surprised
  4. RuthWith a cardboard box and a lot of nerve. I was shaking the whole time.Gacrux · wry
  5. InterviewerWhat surprised you most in that first year?Iapetus · gentle
  6. RuthHow calm they are when you're calm. They read you. If you rush, they know.Gacrux · thoughtful, slow
  7. InterviewerAnd the neighbours? Did they mind?Iapetus · light
  8. RuthThey did, until the first jar of honey. Now they ask me when the next harvest is.Gacrux · dry, smiling
  9. InterviewerLast question. What would you tell someone thinking about starting?Iapetus · warm
  10. RuthFind a mentor, start with one hive, and never wear perfume to an inspection.Gacrux · firm, amused

A made-up interview written for this demo, voiced with AI voices.

Interview Transcript to Audio

Features & capabilities

What you get, from manuscript to finished audiobook.

  • Q&A turns detected

    Names or roles in front of each turn are read as speakers, and the AI follows the back-and-forth of questions and answers.
  • Interviewer, guests, narrator

    One voice asks, another answers, and a panel can have a voice per guest. An optional narrator reads the intro and any context between sections.
  • Upload the file you have

    Transcripts arrive as Word documents, PDFs or plain text. Upload TXT, MD, DOCX, PDF or EPUB, up to 60 MB, or paste the text directly.
  • Delivery notes in brackets

    A written answer loses its tone. Add a note such as [laugh], [pauses, thinking] or [warmly] before a line to bring the conversation back.
  • Chapters for long interviews

    Split an hour-long interview into topics. Export an M4B with chapter marks, one MP3, or a ZIP with one MP3 per chapter.
  • Fix one answer

    Corrected a name or a figure? Regenerate that single line instead of the whole interview.

Script template

Copy an interview transcript template

Replace the text in brackets with your own, paste it into the studio, and every speaker gets a voice.

Interview transcript template

A name or role before every turn, one turn per paragraph. Unlabelled text, such as the intro, goes to the narrator. Replace the brackets with your interview.

NARRATOR: This interview with [GUEST NAME], [GUEST ROLE], was recorded on [DATE] and is read here by AI voices.
INTERVIEWER: [GUEST NAME], thanks for doing this. Let's start at the beginning. [OPENING QUESTION]
[GUEST NAME]: [laugh] [Short, warm opening answer.]
INTERVIEWER: [Follow-up that picks up a detail from the answer.]
[GUEST NAME]: [Longer answer. Split it into two paragraphs if it runs past four sentences.]
[GUEST NAME]: [Second paragraph of the same answer.]
INTERVIEWER: [Question about the hardest moment.]
[GUEST NAME]: (pauses, thinking) [Considered answer.]
INTERVIEWER: [Question about a specific example, number or name. Spell names the way they sound.]
[GUEST NAME]: [Answer.]
NARRATOR: [Optional section break, e.g. "Part two: what comes next."]
INTERVIEWER: [Forward-looking question.]
[GUEST NAME]: [Answer.]
INTERVIEWER: Last question. [ADVICE QUESTION]
[GUEST NAME]: [Short, quotable closing answer.]
INTERVIEWER: [GUEST NAME], thank you.
[GUEST NAME]: (warmly) Thank you for having me.

For a panel, add one label per guest, such as [GUEST 2 NAME]:. Delete timestamps, [inaudible] and [crosstalk] from real transcripts before pasting.

Use cases

What can you make with Interview Transcript to Audio?

Where authors and storytellers put it to work.

  • Written Q&A as an episode

    Turn a newsletter or blog interview, or one done over email, into an audio episode for readers who would rather listen.
  • Research and stakeholder playback

    Re-voice anonymized research interview excerpts so a team hears the conversation without hearing the participant's real voice.
  • Translated interviews

    Voice the translated transcript of an interview held in another language, with the same two-voice structure as the original.
  • Interview practice

    Write out the questions you expect and your answers, then listen back as a two-voice mock interview while you commute.

Hear example character voices

Demo performances. In the studio you cast from standard and premium voice lists.

More examples
On this page
  1. 1Interview transcript to audio, without a studio
  2. 2Clean the transcript before you upload it
  3. 3Speaker labels that detect cleanly
  4. 4Choosing voices for the interviewer and the guest
  5. 5Bringing the conversation back to life
  6. 6Export, length and credits

In depth

Interview transcript to audio, without a studio

Turning an interview transcript to audio gives a written conversation back its voices. Maybe the Q&A was done over email, the recording is too noisy to publish, the interview ran in print and you want an audio edition, or the transcript is all you were allowed to keep. In each case you have the words and need a listenable version with one voice asking and another answering.

FullCastBook reads the transcript, assigns every turn to the interviewer or a guest, and voices each with a different AI voice. You check the speakers, choose the voices and download the conversation as one file. It runs on the same engine as our multiple voices text to speech tool, set up here for interviews rather than scripts or stories.

Clean the transcript before you upload it

Transcription tools leave things a listener doesn't need. Remove timestamps like 00:12:31, the "Speaker 1" and "Speaker 2" labels (replace them with names or roles), and the filler words you would cut in an edit: most "um", "you know" and false starts. Keep a few if you want the conversation to sound unscripted.

Watch the square brackets. Transcripts often contain [inaudible], [crosstalk] or [laughter], and in the studio square brackets are read as delivery notes and sound tags. Delete the ones you don't want heard, and turn the useful ones into tags the voices understand, such as [laugh] for [laughter]. Gaps marked [inaudible] are best fixed or cut in the text, since a voice can't guess what was said.

Then decide how faithful the audio should be. A verbatim re-voicing keeps every answer as given, which suits research and archives. An edited version trims tangents, merges repeated points and reorders a question or two, which suits an episode. Either way, keep the guest's meaning intact, and if you edit their answers, say so in the intro or the show notes.

Speaker labels that detect cleanly

The clearest format is a name or role before each turn: "INTERVIEWER:" and "RUTH OKAFOR:", or a short first name. Use the same label every time. Single-letter labels like "Q:" and "A:" are best renamed, because a short, real name leaves less room for doubt and makes the speaker list easy to read. Magazine-style Q&As with the interviewer's question in bold and the answer below usually work too; check the result in the studio.

Panels and group interviews work the same way: every guest with their own label becomes a speaker with their own voice. If there's an introduction, a short bio or a scene-setting paragraph without a label, it goes to the narrator, which makes a natural opening for an episode.

Choosing voices for the interviewer and the guest

Contrast keeps listeners oriented. If the interviewer and guest are similar in age and pitch, a long answer can make people lose track of who is speaking. Pair a clear, even voice for the interviewer with a voice that suits the guest, such as an older, warmer voice for a retired craftsman or a quick, bright one for a young founder. If the original recording exists, listen to a minute of it first so the voice you pick fits the guest's age and manner.

These are AI voices, not the speakers' real voices: FullCastBook has no voice cloning. That matters for honesty. Tell listeners the interview is re-voiced with AI, credit the real people by name, and get the interviewee's agreement before you publish their words as audio, especially if the original interview was given for print.

Bringing the conversation back to life

Written answers are tidier than speech, so a direct read can sound like an essay. A few bracketed notes help: [laugh] where the guest laughed, [pauses, thinking] before a difficult answer, [warmly] for a thank-you. Mark the moments that matter rather than every line. If an answer still sounds wrong, change the note and regenerate that line. See AI voice emotion tags for notes that work well.

Long answers read better in shorter paragraphs, which give the voice natural places to breathe. Names, places and technical terms are worth one check before export; if one is mispronounced, spell it the way it sounds, as the pronunciation guide explains.

Export, length and credits

A short Q&A downloads as one MP3. For a long interview, put each topic in its own chapter and export an M4B with chapter marks, or a ZIP with one MP3 per chapter. There are no per-line files and no video; the result is audio you can publish as a podcast episode, attach to an article or edit further. For a scripted show rather than a transcript, see two-host podcast script to audio.

Signing up is free and needs no card. Generating and exporting use credits, counted by the characters voiced, so a long interview costs more than a short one, and regenerating a line uses credits again. Compare the plans before you voice a full hour.

Tips

Tips for turning a transcript into audio

  1. Rename generic labels

    Replace "Speaker 1", "Q:" and "A:" with roles or names. One consistent label per person gives the cleanest speaker list.
  2. Strip timestamps and markers

    Delete 00:12:31-style timestamps and transcription notes like [inaudible] or [crosstalk]. Square brackets are read as delivery notes in the studio.
  3. Turn [laughter] into [laugh]

    Keep the reactions worth hearing, but as tags the voices know, such as [laugh] or [sigh], placed in the line where they happened.
  4. Trim the filler, not all of it

    Cut most "um" and false starts, which sound odd from a clean AI voice, but keep a few natural turns of phrase so it doesn't read like an essay.
  5. Break up long answers

    Split answers longer than four or five sentences into paragraphs. The voice gets natural pauses, and you can regenerate a smaller piece.
  6. Check names and numbers

    Listen once to every proper name, place and figure. Spell a mispronounced name the way it sounds and regenerate just that line.
  7. Disclose and get consent

    Say in the intro that the interview is read by AI voices, and ask the interviewee before publishing their words as audio.

FAQ

Interview Transcript to Audio: FAQ

Something not covered here? Email us at support@fullcastbook.com

How do I turn an interview transcript into audio with two voices?

Paste or upload the transcript with a name before each turn, and FullCastBook gives the interviewer and the guest different AI voices and returns one MP3. You can change either voice and reassign any line before you generate.

Can I convert a Q&A article into a podcast episode?

Yes. Label the questions and answers with names, add a short intro for the narrator if you like, and export the conversation as an MP3. Ask the interviewee before you publish their answers as audio.

Will the AI voice sound like the person who was interviewed?

No. FullCastBook has no voice cloning; every speaker gets a stock AI voice. Tell listeners the interview has been re-voiced with AI voices.

My transcript says Speaker 1 and Speaker 2. Will that work?

It works, but renaming them to roles or names, like INTERVIEWER and the guest's name, gives a clearer speaker list. Also remove timestamps and bracketed notes like [crosstalk] before uploading.

Can it handle a panel with more than one guest?

Yes. Every labelled speaker becomes a separate voice, so an interviewer and three panelists get four voices. Choose voices that differ clearly so listeners can follow.

How long can the interview be?

You can upload a transcript file of up to 60 MB, which is far longer than most interviews. Split long interviews into chapters by topic and export an M4B or one MP3 per chapter.

Is it free to convert a transcript to audio?

Signing up is free with no card, and voice samples are free to hear. Generating and exporting audio use credits; see pricing.

Give your interview its voices back.

Upload a transcript, choose a voice for the interviewer and each guest, and download the conversation as one MP3. Free to sign up; pay with credits when you create.