Creative AI
Collection No. 01 — 1,000 Fish Audio Ideas

Creative AI

One thousand conceptual threads where the world's creative disciplines meet a real voice primitive — Fish Audio text-to-speech, spoken voice loops, realtime transcription, and voices you design or clone — each one ready to ship in a single Lovable build.

Browse the IndexGet an API Key ↗
Primary Directive · dance

Lineage Socratic Tutor

Lovable AI explores cultural roots so students respect dance lineage; Fish Audio speaks history through interactive dialogue.

View Entry
02

Alt-Text Weaver

Theme · video
1kOnchain Entries
Section II

Four voice primitives.

Streaming TTS, conversational agents, realtime transcription, voice design & cloning — the four kernels every entry leans on.

Appendix · Build Strategy

The One-Key Protocol

One API key, one Lovable build, every demo streaming real Fish Audio voice.

→
Status

Streaming on Fish Audio.

Chapter I · Disciplines

Ten houses, one voice stack.

See full index →
💃01/10
Dance & Choreography
100 entries →
🎵02/10
Music & Sound Design
100 entries →
🎨03/10
Visual Art
100 entries →
🎥04/10
Videography & Film
100 entries →
📷05/10
Photography
100 entries →
✍️06/10
Writing, Poetry & Narrative
100 entries →
🎬07/10
Filmmaking & Animation
100 entries →
🎮08/10
Game Design & Interactive Media
100 entries →
🎭09/10
Theater & Live Performance
100 entries →
👗10/10
Fashion & Textile Design
100 entries →
Chapter II · Primitives

The four kernels.

Read the primer →
streaming voice№ 01
Fish Audio Text-to-Speech
a POST to https://api.fish.audio/v1/tts with the `model: s2.1-pro` header that returns MP3 / WAV / PCM / Opus bytes and plays them as the user reads or interacts
live conversation№ 02
Voice Loop Agent
a full spoken round trip — browser MediaRecorder captures the question, /v1/asr transcribes it, Lovable AI answers it, /v1/tts speaks the answer back
live transcription№ 03
Speech-to-Text with Timestamps
Fish Audio /v1/asr with `ignore_timestamps=false` — the client posts recorded audio chunks as multipart form data and gets back text plus per-segment start/end times
custom voices№ 04
Voice Design & Cloning
Fish Audio /v1/voice-design (model header `voice-design-1`) invents candidate voices from a written description, and POST /model clones a voice from a reference clip for reuse via `reference_id`
Chapter III · Method

Three movements, ten minutes.

  1. Movement 0101
    Choose a house
    Skim ten disciplines. Open the one that suits your team.
  2. Movement 0202
    Read an entry
    Pitch, voice primitive, plain-language proposition, market sizing.
  3. Movement 0303
    Copy the mega-prompt
    Add one secret, paste into Lovable, stream real voice. Ship.

1,000 entries indexed · zero infra · ready to stream