moritz/mop-skills
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fix(text-to-audio): add parallel chunk synthesis, automatic MiniMax fallback, voice normalization, and streaming progress

Browse Source
This commit is contained in:
Moritz Graf
2026-09-08 20:13:29 +02:00
parent 9ac1ee5f35
commit fbd934965d
3 changed files with 337 additions and 189 deletions
Download Patch File Download Diff File Expand all files Collapse all files
AGENTS.md
+2 -2
View File
@@ -33,8 +33,8 @@ Real-time public transport information for Regensburg (RVV). Provides departures
### [text-to-audio](skills/text-to-audio/SKILL.md)
Audio dossier and podcast producer. Converts arbitrary research, summaries, notes, or articles into audio dossiers with duration target, importance compression, and solo or NotebookLM-style dialogue.
- **Features:** Target duration pacing (~130 words/min), importance filtering, solo monologue or multi-speaker dialogue.
- **Voices:** OpenRouter `deepgram/aura-2` with German voices (`aura-2-julius-de`, `aura-2-lara-de`) and English voices (`aura-2-zeus-en`, `aura-2-athena-en`).
- **Tools:** Includes `scripts/text_to_audio.py` for API synthesis, multi-voice stitching, and MP3 generation.
- **Voices:** Primary Google Gemini 3.1 Flash TTS with automatic MiniMax Speech 02 HD fallback. German voices (`Puck` host/solo, `Aoede` co-host, `Charon` deep), English voices (`Zephyr` host/solo, `Aoede` co-host).
- **Tools:** Includes `scripts/text_to_audio.py` for parallel chunk synthesis, auto-fallback, and MP3 generation.
### [skill-creator](skills/skill-creator/SKILL.md)
Guidelines and scripts to help developers build high-quality, token-efficient Claude skills.