What do you want?
Hello Min and the SkyrimNet development team!
First of all, thank you so much for the incredible work on this passion project. It has completely changed my Skyrim experience!
I would like to respectfully request the addition of "Cartesia" as a supported external Cloud TTS provider.
Why?
The Use Case & Reasoning:
Currently, for non-English players (especially Japanese users), the viable options for Cloud TTS are extremely limited:
- ElevenLabs is fantastic and the best quality, but it is very expensive to use as a primary TTS for everyone.
- Inworld TTS recently had a massive price increase (5x), making it hard to justify for regular playthroughs. Furthermore, Inworld struggles significantly with the Japanese language, often mispronouncing words, reading them with a heavy English accent, or failing to parse audio tags properly.（There are many misreadings of kanji characters, and without subtitles, it's impossible to understand what's being said, which diminishes the immersion for VR players.）
- Local TTS options (XTTS, Zonos.) are great, but they require significant VRAM and PC resources (or Vast.ai setups) which isn't always an option for players with heavy modlists.
- Other local TTS programs do not work in Japanese.
Cartesia is known for its high-quality, realistic voices and low latency, making it perfect for real-time NPC conversations. When I was using CHIM, it wasn't quite as good as ElevenLab, but I preferred using Cartesia for NPCs other than followers because of its high-quality Japanese language support and low price.
Adding Cartesia would provide a much-needed, high-quality, and affordable cloud TTS alternative for users playing in Japanese and other non-English languages, without melting our GPUs!
What area does this affect?
Voice / TTS
How should it work?
No response
Scope
Small tweak (config option, UI adjustment, minor behavior change)
Alternatives or workarounds
No response
Anything else?
Thank you so much for your time and consideration!
What do you want?
Hello Min and the SkyrimNet development team!
First of all, thank you so much for the incredible work on this passion project. It has completely changed my Skyrim experience!
I would like to respectfully request the addition of "Cartesia" as a supported external Cloud TTS provider.
Why?
The Use Case & Reasoning:
Currently, for non-English players (especially Japanese users), the viable options for Cloud TTS are extremely limited:
Cartesia is known for its high-quality, realistic voices and low latency, making it perfect for real-time NPC conversations. When I was using CHIM, it wasn't quite as good as ElevenLab, but I preferred using Cartesia for NPCs other than followers because of its high-quality Japanese language support and low price.
Adding Cartesia would provide a much-needed, high-quality, and affordable cloud TTS alternative for users playing in Japanese and other non-English languages, without melting our GPUs!
What area does this affect?
Voice / TTS
How should it work?
No response
Scope
Small tweak (config option, UI adjustment, minor behavior change)
Alternatives or workarounds
No response
Anything else?
Thank you so much for your time and consideration!