Podcasters & video creators
From raw audio to published episode.
Transcribe the episode, draft show notes, narrate with TTS, and cut teaser clips.
Every episode spawns five downstream deliverables.
Transcript, show notes, titles, narration, and teasers come out of the same thread as the audio.
Transcription, notes, and clips each have their own tool.
Transcription, text models, TTS voices, and video models work in the same workspace on the same files.
Voiceover retakes burn studio time.
TTS narration regenerates in seconds from an edited script, in a voice you pick.
Transcribe the episode
Upload the recording; speech-to-text makes the whole episode searchable and quotable.
More about TranscriptionDraft the package
Show notes, titles, and chapter markers from several models; keep the strongest take.
More about Multi-Model ChatNarrate the extras
Intros, ads, and corrections in a TTS voice; regenerate in seconds when the script changes.
More about Audio GenerationCut the teasers
Short clips from video models for the feed. Video generation has no free lane: clips bill per second at the rates shown in the app.
More about Video GenerationWhat this replaces
Built from these features
Transcription
Dictate messages and transcribe recordings, accurately, in any chat.
Audio Generation
Dozens of voices for text to speech, plus fast accurate transcription: in every chat.
Video Generation
Veo, Runway, Kling, Luma: short clips generated in chat, saved to your Drive.
Multi-Model Chat
GPT, Claude, Gemini, Grok, Llama: pick mid-conversation, cheapest-first.
Drive
Folders, previews, and lightweight versioning for AI work.