Expired85% confidenceFactTime unknown
The blogger used a local TTS model called 'Fish Speech S2 Pro' to clone a real person's voice for the desktop pet's dubbing.
1
Sources
85%
Confidence
Medium-term (~90 days)
Relevance
6/1/2026
First Seen
Valid until: 8/30/2026(expired)
Sources
Codex桌面宠物实战：从零打造会说话的AI小精灵
bilibili灵姐说AI
Related Entities
Related Claims
UnverifiedFish Audio是一款基于深度学习的文本转语音（TTS）服务，支持多种音色克隆和自然语音合成78% similarUnverifiedFish Speech是一个开源的文本转语音模型，其S2 Pro版本支持零样本和少样本声音克隆，只需几秒到几十秒的参考音频即可生成高度相似的合成语音74% similarUnverifiedThe narration audio of the video is itself generated by the local model of this TTS application, forming a bootstrapped demonstration.70% similarUnverifiedModern voice cloning solutions typically use a speaker encoder to map a voice into a high-dimensional embedding vector, which is then injected into the acoustic model during the TTS decoding stage to control the output timbre.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/25993API
curl https://kongchang.com/api/v1/knowledge/claims/25993MCP
get_claim(id=25993)