(TODO) Audio
how to get an audio file
- long
- short
- sync
- audio
- timecode with text
AI
TODO Suno
TODO Elenglab
TODO Adobe
https://www.adobe.com/products/firefly/features/sound-effect-generator.
The services for SFX and Music generally fall into two categories: Library/Search (for existing assets) and Generative (for creating new assets).
Here is a combined table showing the API availability for both Search/Library and Generative functionality for the services you mentioned.
| Service | Primary Category | API for Generation | API for Search/Library | Notes |
|---|---|---|---|---|
| Freesound.org | SFX / Library | No | [ ] Yes | Offers a comprehensive API for searching, browsing, and retrieving sound effects based on keywords and content analysis. |
| Unity Asset Store | SFX & Music / Library | No | Yes (In-Editor) | Search functionality is accessible programmatically within the Unity Editor using its specialized search provider. |
| ElevenLabs | Voice/SFX / Generative | [ ] Yes | No (Library) | Primarily a Text-to-Speech (TTS) and Text-to-SFX generation API. No API for searching a public library of existing SFX. |
| Audo.ai | Audio Processing | No | No | The API is for noise removal and speech enhancement, not for generating or searching a music/SFX library. |
| AIVA | Music / Generative | Yes | Unconfirmed | Focused on generating music based on parameters. API access is primarily for generation. Public search API is not explicitly documented. |
| Soundraw | Music / Generative | [ ] Yes | [ ] Yes (By Criteria) | API for generating original music based on parameters (genre, mood, etc.). This acts as a search by criteria for original content. |
| Mubert | Music / Generative & Library | [ ] Yes | [ ] Yes | Offers both a generative API (Text-to-Music, Image-to-Music) and access to a curated library that can be filtered by genre, mood, or BPM. |
| Amazon Polly | Voice / Generative | Yes | No | Text-to-Speech (TTS) API. No API for searching a music/SFX library. |
| Google Gemini/TTS | Voice / Generative | Yes | No | Text-to-Speech (TTS) via the Gemini API or Cloud TTS. No API for searching a music/SFX library. |
Key Takeaways:
- For finding existing SFX/sounds, Freesound.org is the primary service with a search API.
- For generative music that acts as a search-by-criteria, Soundraw and Mubert both offer APIs.
- Mubert is unique in that it offers both music generation and search/filtering on its curated tracks.
How to Convert Text to Speech in Python
- gTTS
- pyttsx3
- openai
- Huggingface Transformers
tts
https://ttsmaker.com/#google_vignette
私の 父さん は すてき=> ttsmaker-file-2025-2-26-10-52-48.mp3 mv TTS/ttsmaker-file-2025-2-26-10-52-48.mp3 Solar2D/kwik-editor-proj/Solar2D/App/lingualSample/assets/audios/sync/ja/my_father_is_nice.mp3
online
offline
https://www.rcnp.osaka-u.ac.jp/~kohda/linux/espeak.html
sudo apt install espeak $ espeak -v +f3 -s 140 "Hello World!"
open jtalk