Unverified50% confidenceFactExact time
The competitive landscape for voice models includes Cartesia (Sonic 3.6), OpenAI (GPT-4o mini TTS), Google (Gemini Flash TTS), as well as startups such as Deepgram, Fish Audio, and Boson.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/13/2026
First Seen
Valid until: 10/27/2026
Sources
Related Entities
Related Claims
UnverifiedOpenAI的GPT-Live语音模型采用端到端架构，原始音频波形直接输入模型，模型直接输出音频，中间不再经过独立的ASR和TTS模块68% similarUnverifiedGoogle的AudioLM（2022）和Meta的SeamlessM4T（2023）验证了直接在音频域进行建模的可行性68% similarUnverifiedOpenAI discovered a rare unauthorized voice generation phenomenon in the GPT-4o system card, where the model unexpectedly mimics the user's own voice.68% similarUnverifiedGoogle has brought next-generation text-to-speech (TTS) capabilities to Gemini Audio.68% similarUnverified2023年后，随着Whisper、Bark、VALL-E等开源模型的广泛传播，从频谱图还原语音的能力已不再局限于顶级研究机构，普通技术人员借助消费级GPU即可复现67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1020019API
curl https://kongchang.com/api/v1/knowledge/claims/1020019MCP
get_claim(id=1020019)