Armin Ronacher on Qwen3-TTS: custom game narrator voices, cloning limits and workarounds
mitsuhiko · x · 2026-10-30
Armin Ronacher shares hands-on learnings from building a dungeon crawler with his kids, using Qwen3-TTS for narrator voice overs with custom voices. Qwen3-TTS ships three 1.7B variants: Base (clones from seconds of reference audio), CustomVoice (nine built-in speakers with instruction control), and VoiceDesign (invents a voice from a text description). Key limitation: the Base model cannot combine voice cloning with instruction control — no "speak sad" or "whisper" on a cloned voice. The practical path for unique voices is generating a clip with VoiceDesign, then cloning it with Base. He compares it with Kokoro and includes examples and pitfalls you can hand straight to an agent.
More from coding & agent
- iOS agent factory autonomously fixes its own stale bundle ID bug via self-improvement PR — vikvang1 · 2026-10-30
- Global Law as one Git history: HN #1 repo makes world law queryable by AI agents — SnooPeripherals5313 · 2026-10-30
- Fine-tuning Liquid d1 decision models on screenshots: 51% to 96% accuracy in ~20 minutes — helloiamleonie · 2026-10-30
- Measuring compaction on a 400k-token session: 38s and $1.99 per run — brandon_galang · 2026-10-30
- pstack's /statechart skill ships with a mini TLC compiler that helped find real distributed-systems bugs — DavidKPiano · 2026-10-30
- First video demo: using Grok bot for daily workflow, outer vs inner loop — fbaptista · 2026-10-30