Unverified50% confidenceBenchmarkExact time
The TTS voice model's weights are approximately 4.5 GB, with measured usage at 4.7–4.8 GB, because TTS is stateless between requests and has no long context or queue buffers.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedWhen running Whisper ASR, a TTS voice model, and nomic-embed-text simultaneously on an RTX 3090 with 24 GB of VRAM, the three resident models occupied 17.8 GB (72%) of VRAM, peaked at 23.4 GB over the course of a week, and never spilled over into system memory.76% similarUnverifiedTTM 模型参数量仅约 0.8M（百万级），文件大小约三兆字节，无需 GPU，在普通 CPU 上就能运行68% similarUnverified语音Agent典型端到端延迟预算约为STT finalization 100-300ms + LLM TTFT 200-500ms + TTS TTFA 150-250ms + 网络开销50-100ms，总计500-1150ms65% similarUnverifiedThrough request-owned speculative KV, in a DeepSeek-V4-Pro 1P1D, MI355X, concurrency-256 scenario, the average TTFT was reduced from 19.4 seconds to 15.1 seconds.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1002814API
curl https://kongchang.com/api/v1/knowledge/claims/1002814MCP
get_claim(id=1002814)