Changelog

New features, improvements and account changes in AIdeaFlow Podcast, newest first.

  1. New

    Smart rewind, volume boost and saving a clip

    The episode player has five more listening tools. They run in your browser; a saved clip is encoded there, and nothing is sent to a server.

    • After you pause, playback can rewind a little when you press play again. The longer the pause, the farther it goes back, and it never leaves a marked loop. You can turn this off.
    • Raise the volume by 6 or 12 dB for a quiet room or a phone speaker. A limiter keeps the audio from clipping. This is separate from clearer speech.
    • Save the marked loop, or the current spoken turn, as a WAV file on your device. Clips are at most two minutes.
    • Open a waveform of the episode to see loudness and jump to a point. It is computed in the tab when you ask for it.
    • On episodes with timed turns, listen to one host only. Playback skips the other host's turns.
    Listen to an episode
  2. New

    Floating captions, keyboard shortcuts and sharing a moment

    The episode player has five more listening tools. They run in your browser; your listening map stays in its local storage, and your practice recordings are never uploaded.

    • On episodes with timed turns, open floating captions: a small window that stays on top of other windows and shows who is speaking and what they say, with play, pause and skip buttons. It needs a browser that supports Document Picture-in-Picture, such as a recent Chrome or Edge on a computer.
    • Control the player from the keyboard: Space or K to play and pause, J and L to skip, Shift and the arrow keys to move between spoken turns, comma and period to change the speed, B to add a bookmark, M to mute, and ? to see the list. You can turn the shortcuts off.
    • A thin bar under the player shows which parts of the episode you have already heard, across visits. Jump to the next part you have not heard, or clear the map.
    • On episodes with timed turns, record yourself saying the current turn, then play the original turn and your recording one after the other. The recording stays in the browser tab until you discard it or leave the page.
    • Share this moment: on a public episode, share or copy a link that starts at the current spoken turn, with a short quote of it.
    Listen to an episode
  3. Improvement

    Clear speech, mono, study ambience and host focus are back

    The four sound effects in the episode player work on episodes again, and they never silence an episode.

    • Turn on clear speech, play in mono, add study ambience, or focus on one host while an episode plays.
    • If your browser cannot apply an effect to a particular episode, the episode keeps playing normally from the same spot and the player tells you the effect is unavailable.
    Listen to an episode
  4. New

    Turn images into a podcast

    The podcast generator now reads images. Upload screenshots, slides, photos, whiteboards, charts or handwritten notes, and the text and content they show become the source of your podcast.

    • Add up to 6 PNG, JPEG, WebP or GIF images of 5 MB or less each, by dropping them on the generator or choosing them. Each image shows as a thumbnail that you can remove.
    • Click Read images: the text of the images and a description of their charts and diagrams go into the input box, where you can edit them before you generate.
    • Image upload is part of the import tools of the Freelancer, Professional and Enterprise plans, and each read counts toward the assistant limit of your plan. The images are not saved to your account.
    Open the podcast generator
  5. New

    Sleep timer, resume, bookmarks and lock-screen controls

    The episode player now has five more listening tools. They run in your browser and keep their data in its local storage; nothing is sent to our servers.

    • Set a sleep timer for 5, 15, 30 or 45 minutes, or to the end of the current chapter. The volume fades over the last 8 seconds, then the episode pauses.
    • Come back to an episode and pick up at the spot where you left off.
    • Control playback from the lock screen or your system media keys: play, pause, skip, seek, and jump between chapters.
    • Add bookmarks at any moment, jump back to them, and delete them when you are done. Each episode keeps up to 50.
    • On episodes with timed turns, turn on even pace to keep the speaking rate steady from one turn to the next.
    Listen to an episode
  6. New

    The Voice Library and voice cloning

    Each host's voice now opens a voice picker: the featured voices, a search of the ElevenLabs Voice Library, and your own voice clones.

    • Search thousands of Voice Library voices in 80 languages, filter by language, gender, age and accent, and play a sample before you pick one. Every paid plan can use them.
    • Clone a voice from one to three short recordings. The Professional plan keeps 1 voice clone and the Enterprise plan 3; only you can use your clones, and you can delete them at any time.
    Open the podcast generator
  7. Improvement

    80 spoken languages and clearer audio

    The spoken language list now covers every language of the Expressive model, generated audio is encoded at a higher bitrate, and podcasts are read faster.

    • Pick from about 80 spoken languages, including Hebrew, Turkish, Vietnamese, Thai and Ukrainian. Expressive locks every language; Flash locks the 32 it speaks and detects the rest.
    • Generated audio is now MP3 at 192 kbps instead of 128 kbps.
    • More lines are spoken at the same time, so long podcasts finish sooner.
    Open the podcast generator
  8. Improvement

    Skip fillers, repeat a turn, and study listening

    You can now drop spoken fillers such as um and uh from generated audio, repeat the current turn, skip pauses between turns, hide unread lines until they have been heard, and fold stereo playback to mono.

    • Skip fillers such as um and uh in the spoken audio. The transcript keeps the original wording.
    • Repeat the current spoken turn on a timed episode.
    • Skip the pauses between turns while you listen.
    • Hide unread lines until that turn has been heard.
    • Fold stereo playback to mono in the player. The audio stays in your tab.
    Open the podcast generator
  9. Improvement

    Room wetness, spoken mood, and study listening

    You can now set how much of the voice goes into the room, give Expressive episodes a spoken mood, mix a study bed in the player, pause after each turn to repeat it, and replay the last spoken word.

    • When a room is set, send less of the voice into that room, or keep the full echo.
    • On the Expressive voice model, start every turn curious, excited, whispered, or shouted.
    • Mix a cafe, office, or rain bed in the player. The audio stays in your tab.
    • Pause two or four seconds after each spoken turn so you can repeat it.
    • Replay the last spoken word on a timed episode.
    Open the podcast generator
  10. Improvement

    Room sound, host placement, and turn listening

    You can now place the hosts in a room, sit them left and right, and keep or drop the intonation between turns. On a timed episode you can skip by spoken turn and duck the other host.

    • Place the hosts in a small room or a hall. The room is stereo and adds a short tail after each turn.
    • Sit host 1 on the left and host 2 on the right, or keep both in the centre.
    • Keep neighbouring lines as context so the pitch can flow, or start each turn on its own.
    • Skip to the next or previous spoken turn on a timed episode.
    • Hear one host more clearly by ducking the other host's turns in the player.
    Open the podcast generator
  11. Improvement

    Voice colour, repeatable delivery, and study listening

    You can now colour the hosts as a phone, an old radio or a robot, lock or vary the delivery from turn to turn, and turn speaker boost off. On an episode you can loop a section and search the timed transcript.

    • Colour the generated voice as a phone, an old radio, or a robot, without adding a room echo.
    • Lock the delivery so turns stay closer, or vary it on each turn.
    • Turn off speaker boost when the original recording artefacts are too strong.
    • Search the timed transcript and jump to a spoken word on a new episode.
    • Mark a start and an end on the player and loop that section.
    Open the podcast generator
  12. Improvement

    Closer voices, clearer numbers, and word follow-along

    You can now choose how closely the hosts match their voices, how strongly to colour the delivery, how numbers are read, and how far they sound. New episodes highlight each spoken word as you listen.

    • Match the chosen voice more loosely or more closely, and exaggerate its character.
    • Always read numbers and dates in full, or keep digits as written.
    • Move the hosts a little farther from the microphone, without adding a room echo.
    • On a new episode, click a word in the player to jump to that moment.
    Open the podcast generator
  13. Improvement

    Spoken delivery controls and clearer speech

    You can now set how fast and how steadily the hosts speak, and keep names and acronyms pronounced the way you want. The player has a new clearer-speech option.

    • Slow down or speed up the spoken delivery, and pick a livelier or a steadier voice.
    • Lock the spoken language on the Flash and Expressive voice models, so a host stays in the language of the episode.
    • Rewrite names and acronyms for speech before the audio is made.
    • On the Expressive voice model, keep audio tags such as laughs and sighs in the script.
    • The clearer-speech option runs in your browser. The audio is not sent anywhere.
    Open the podcast generator
  14. Account

    Buy a plan before you create an account

    The pricing page now takes you straight to checkout, without a sign-in first. The plan goes to the email address you enter at checkout.

    • A new address gets a new account, and you are signed in right after the payment.
    • If the address already has an account, the plan goes to that account. Sign in with the email link to use it.
    See the plans
  15. New

    Chapters, playback controls and conversation options

    New episodes have chapters, speed and skip controls, and a transcript you can click to jump to a line. In the generator you can name the hosts, choose who speaks first, pick a conversation style and add a pause between turns.

    • Chapters of about 90 seconds each, as a list you can click and as a WebVTT chapters file.
    • Playback speed from 0.75× to 2×, and buttons that skip 15 seconds back or forward.
    • Four conversation styles: balanced, interview, debate and explainer.
    • A pause of 0.25, 0.5 or 0.8 seconds between turns, also for a script that you write yourself.
    Make an episode
  16. New

    SRT and WebVTT subtitles

    Download subtitles for new episodes as SRT or WebVTT files, timed from each spoken turn.

    • The subtitle downloads are on the episode page, next to the audio and the transcript.
    • Episodes made before this release keep the plain-text transcript download.
    Listen to public episodes
  17. Improvement

    A new studio with ElevenLabs voices

    AIdeaFlow Podcast has a new design, and every episode is now voiced by ElevenLabs with three voice models: Flash, Multilingual and Expressive.

    • The site is available in 12 languages, with right-to-left layouts for Hebrew and Arabic.
    • Each plan card shows the episode length, the voices and the monthly audio of the plan.
    Open the podcast generator
  18. Improvement

    Your podcasts: a public switch and downloads

    Your podcast library now shows 24 episodes per page, and each episode has a switch that makes it public or private.

    • Episode pages offer the audio and the transcript as downloads.
    • The audio download names its real format: MP3 for new episodes, WAV for some older ones.
    • When you delete an episode, its audio and transcript files are deleted too.
    Open your podcasts
  19. Improvement

    Episodes finish after you close the tab

    Generation now runs on our servers until the episode is saved, so you can close the browser tab and find the episode in Your podcasts later.

    Open your podcasts

Ready to try the latest features?

Account holders get a short email when new features ship. Every email has an unsubscribe link.