Unverified50% confidenceFactExact time
Models that truly natively support speech output (such as GPT-4o's real-time voice mode) adopt an approach of directly modeling speech tokens, skipping the intermediate text state, but such models are usually closed-source, difficult to deploy privately, and perform worse than pure-text reasoning models on complex tasks such as tool calling.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/15/2026
First Seen
Valid until: 1/13/2027
Sources
Related Entities
Related Claims
UnverifiedCommonly used industry solutions include Twilio Voice API for call ingestion, models such as Whisper for transcription, and GPT-4o or similar models for intent understanding and response generation.79% similarUnverifiedOpenAI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79% similarVerifiedEarly ChatGPT voice used a cascaded architecture: first converting speech to text, then having the large language model generate a response, and finally converting it to speech for output.77% similarUnverifiedOpenAI discovered a rare unauthorized voice generation phenomenon in the GPT-4o system card, where the model unexpectedly mimics the user's own voice.77% similarVerifiedThe new generation of voice interaction has shifted to an end-to-end multimodal model architecture that understands and generates directly at the speech signal level, compressing latency and preserving paralinguistic information.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1036764API
curl https://kongchang.com/api/v1/knowledge/claims/1036764MCP
get_claim(id=1036764)