For Podcasters

Audio in. Video podcast out.

Turn the episode you already recorded into a video podcast with AI: a talking host animated from a portrait, visuals that follow the audio, burned-in subtitles and vertical clips. Plus transcription with speaker labels, voice cloning and royalty-free music.

faktry audio suite with tracks, waveform and mixing controls

Your episode is finished. Its video version is not

An audio podcast ends up in a feed and nowhere else, while video platforms want a face, motion or at least a clip with subtitles. Making that version usually means a video editor, an animator and a subtitle service on top of the audio tools you already pay for. In faktry the recording is the starting point for all of it: transcribe it, cut the segments you want, generate a host portrait, animate it from the episode audio or let the audio drive generated visuals, burn in the subtitles and export vertical clips. Every output lands in one library. 

The podcaster toolkit

The video version of your episode, and the audio tools that sit behind it.

Make the video podcast

A talking host from a portrait
Upload a portrait or generate one with an image model, add a segment of your episode audio, and Video Avatar animates the face to speak it. Kling AI Avatar V2 and OmniHuman 1.5 are available. Work through the episode segment by segment.
Visuals that follow the audio
Audio to Video generates a clip driven by a 2 to 20 second piece of audio, and can animate a starting image such as your cover art. Useful for teasers, trailers and the moments where a static card would sit on screen for minutes.
Subtitles and vertical clips
Burn the SRT from your transcript into the video, then reframe to vertical for Shorts, Reels and TikTok. Clip trimming and merging sit in the same video suite.

Produce the audio

Transcription with speaker labels
Transcribe with Whisper-1 or ElevenLabs Scribe v2, which identifies and labels each speaker automatically. Export as plain text, SRT, VTT or timestamped JSON. A 60-minute interview finishes in a couple of minutes.
Voice cloning and speech
Clone your voice from a short sample, then generate sponsor reads, teasers and narration in it. Or pick from ElevenLabs v3, Gemini TTS and OpenAI voices when you want a different narrator.
Music, mixing and cleanup
Generate royalty-free intro and outro music with or without vocals, then mix tracks, trim silence, merge segments and convert between MP3, WAV, OGG, AAC and M4A. No licensing fees for commercial use.

The models behind the workflow

Swap models from a dropdown. Same credit balance, no separate provider accounts.

Transcription, text-to-speech, voice cloning and music generation

  • ElevenLabs
  • OpenAI TTS
  • Gemini TTS
  • MiniMax Music

From audio episode to video podcast

What faktry handles after you stop recording.

Clean up the recording

Trim silence, merge segments, mix in an intro from the music generator and convert to the format you need. Pull guest clips or reference audio from YouTube, SoundCloud, Vimeo or Bandcamp with the audio download.

  • Trim and merge
  • Intro music
  • Audio download

Transcribe the episode

Upload the finished audio and transcribe with Scribe v2. Speaker labels identify each guest automatically. Export SRT for the video version or plain text for anything else.

  • Speaker labels
  • 50+ languages
  • SRT and VTT

Give the episode a face

Generate a host portrait, feed it a segment of the episode audio and animate it into a talking-host clip. For teasers and trailers, let Audio to Video create visuals that follow the sound instead.

  • Host portrait
  • Talking avatar
  • Audio-driven clips

Cut the clips

Burn in the subtitles from the SRT you already have, reframe to vertical and trim the strongest moments into clips for Shorts, Reels and TikTok.

  • Burned subtitles
  • Vertical reframe
  • Clip trimming

Capabilities at a glance

What a podcast account actually touches across the platform.

  • 01Talking-host video from a portrait and your episode audio
  • 02Audio-driven video clips from 2 to 20 seconds of sound
  • 03Speaker diarization on multi-guest interviews
  • 04Transcription in 50+ languages with SRT and VTT export
  • 05Voice cloning from a short reference sample
  • 06Royalty-free music with full commercial rights

Transcription

  • Whisper-1
  • ElevenLabs Scribe v2
  • Speaker labels
  • Timestamped export

Voice

  • Voice cloning
  • ElevenLabs v3
  • Gemini TTS
  • OpenAI TTS

Music

  • Instrumentals
  • Full tracks
  • Sound effects
  • Royalty-free

Video

  • Talking avatar
  • Audio to Video
  • Subtitle burn-in
  • Vertical reframe
  • Yes. Generate or upload a host portrait, add a segment of the episode audio and Video Avatar animates it into a talking-host clip. Audio to Video creates visuals that follow a short piece of audio, subtitles burn in from your transcript, and the video suite reframes everything to vertical. You work segment by segment rather than pressing one button for a full episode.

Pay for the episodes you actually make

Credits instead of four monthly subscriptions. A quiet month costs nothing.