Unverified50% confidenceFactExact time
IboChat's /speak endpoint tries three voice paths in order: GPT-SoVITS (best voice cloning, takes about 5–18 seconds, supports only English, Chinese, Japanese, and Korean, and permanently occupies about 3.9GB of VRAM once loaded), OmniVoice Studio (supports any language, takes about 30–40 seconds, called via an OpenAI-compatible endpoint), and Edge TTS (Microsoft's free neural voices, no cloning capability, supports 24 languages, zero latency, never fails).
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/18/2026
First Seen
Valid until: 1/16/2027
Sources
Related Entities
Related Claims
UnverifiedLoading IboChat's voice model takes about 30–50 seconds; the server first probes whether the model is ready, and if it is not ready it directly falls back to the next tier of voice options rather than making the user wait.73% similarUnverified语音智能体技术栈通常包含STT、LLM推理、TTS三个串行环节，STT约耗时200-400ms，LLM首token延迟约100-500ms，TTS生成约100-300ms70% similarUnverifiedCoqui TTS、VALL-E、OpenVoice 等开源框架已使仅需 3–10 秒音频就能完成基本音色迁移68% similarUnverifiedThe latency budget for one round of conversation in a typical voice agent is approximately: endpoint detection 180ms + streaming ASR 220ms + LLM first token 650ms + TTS first chunk + network transmission.68% similarUnverifiedState-of-the-art real-time speech transcription latency is approximately 200–400 milliseconds, with mainstream industry solutions including OpenAI's Whisper, Google Speech-to-Text, and AssemblyAI.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1057787API
curl https://kongchang.com/api/v1/knowledge/claims/1057787MCP
get_claim(id=1057787)