AI Audio Pro Builder

Music and voice for 24 platforms, text prompt plus JSON · 91 fields · 3 outputs
Library
1 / 91 FIELDS ACTIVE

No JSON - real API exists but native format is Style/Lyrics/Exclude

🔒 Preview mode
Try every field. Unlock AI Audio Pro with Pro to copy and save the prompts.

✨ Enhance with AI
Rewrite the main prompt into 3 polished variations. Pro feature.

01Text Prompt
Fill in the fields above to generate your prompt.
02JSON Output
03Output Metadata
📘 Pro Guide
Key facts
  • SunoNo JSON - real API exists but native format is Style/Lyrics/ExcludeStyle, Lyrics, and Exclude boxes in Suno directly · Uses bracket metatags like [Verse] and [Chorus] inside Lyrics, not JSON or plain prose.
  • UdioYes - Udio APIAPI request body or web app · style_tags is a real array field matching Udio's documented schema.
  • Stable AudioYes - Stability AI APIAPI request body · Genuine text-to-audio API with duration_seconds and steps parameters.
  • AIVAYes - AIVA APIAPI request body or web app · Composition-focused - genre and duration map to real AIVA parameters.
  • MubertYes - Mubert APIAPI request body · Built for streaming/background music generation at scale.
  • Google LyriaYes - Vertex AI APIVertex AI request body · Uses the same instances/parameters wrapper as Google's Imagen API.
  • Meta MusicGenYes - open weights, via Replicate/falAPI request body · Open-weight model - field names depend on your chosen hosting provider.
  • RiffusionYes - open weights, via ReplicateAPI request body · Diffusion-based music generation - newer API surface, verify before production use.
  • Beatoven.aiYes - Beatoven APIAPI request body · Built specifically for background/mood music for video content.
  • SoundrawYes - Soundraw APIAPI request body · Mood and genre driven rather than free-text prompt driven.
  • BoomyUncertain - primarily a consumer appDepends on current developer access · Least documented music platform in this list - verify carefully before relying on its JSON shape.
  • SoundfulYes - Soundful APIAPI request body · Built for creators - genre and mood driven generation.
  • LoudlyYes - Loudly APIAPI request body · Newer platform - verify exact field names against current Loudly docs.
  • ElevenLabsYes - ElevenLabs APIAPI request body · Most thoroughly documented voice API in this list - voice_settings genuinely affects output.
  • Amazon PollyYes - AWS APIAWS SDK or API request body · Uses PascalCase field names (Text, VoiceId), matching AWS API convention.
  • Google Cloud TTSYes - Google Cloud APIAPI request body · Uses the real input/voice/audioConfig structure from Google's documented API.
  • OpenAI TTSYes - OpenAI APIAPI request body · Matches OpenAI's tts-1 model parameters (model, input, voice).
  • Murf AIYes - Murf APIAPI request body · Popular for corporate/e-learning voiceover use cases.
  • Play.htYes - Play.ht APIAPI request body · Real-time and batch voice generation both supported via their API.
  • Descript OverdubUncertain - primarily an editor featureInside the Descript app, not a standalone public API in the same way · Verify current API access before relying on its JSON shape - this is the least certain platform in this list.
  • WellSaid LabsYes - WellSaid APIAPI request body · Newer platform - verify exact field names against current WellSaid docs.
  • LOVO AIYes - LOVO APIAPI request body · Supports speed control as a real API parameter.
  • Resemble AIYes - Resemble APIAPI request body · Voice cloning focused - requires a real voice_uuid and project_uuid from your account.
  • SpeechifyYes - Speechify APIAPI request body · Popular for accessibility and reading-aloud use cases.
View prompts ↓