Unverified50% confidenceFactExact time
The project uses the OpenAI Whisper Large V3 Turbo model for speech transcription, and in measured tests transcribing one sentence costs less than one-thousandth of a cent.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/20/2026
First Seen
Valid until: 11/3/2026
Sources
Building an AI Agent from Scratch in Python: Generate a Complete Scripted Video from Voice
bilibili认真的笨笨10/18/2026
Related Entities
Related Claims
UnverifiedThe project uses the Whisper Large V3 Turbo model, sending Base64-encoded audio data to the /audio/transcriptions endpoint for transcription.76% similarUnverifiedCloud speech API prices are low: Deepgram Nova 3 is approximately $0.004 per minute, and OpenAI mini-transcribe is approximately $0.003 per minute.74% similarUnverifiedThe tool uses the Whisper large v3 model for speech recognition and handles the complete pipeline of downloading, audio extraction, segmentation, recognition, and timestamp alignment.73% similarVerifiedWhisper is an automatic speech recognition model open-sourced by OpenAI in 2022, built on a Transformer architecture and trained on 680,000 hours of multilingual audio data.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1076235API
curl https://kongchang.com/api/v1/knowledge/claims/1076235MCP
get_claim(id=1076235)