Unverified50% confidenceReleaseExact time
Fish Audio released Drama 3 in October 2026, a 35-billion-parameter speech generation model, with weights published on Hugging Face.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/14/2026
First Seen
Valid until: 1/12/2027
Sources
Related Entities
Related Claims
UnverifiedHugging Face launched an open-source text-to-speech leaderboard that evaluates models on three objective metrics: word error rate, real-time factor, and speaker similarity.62% similarUnverifiedv3.29.0 adds the shida voice for Live speech.58% similarUnverifiedThe Big Bench Audio benchmark used by ThunderPhone has been publicly released on Hugging Face, allowing third parties to independently reproduce test results.57% similarUnverifiedWhisper于2022年9月开源发布，后续推出Large-v3版本改善了语音识别准确率56% 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55% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1025048API
curl https://kongchang.com/api/v1/knowledge/claims/1025048MCP
get_claim(id=1025048)