Gemini 3.5 Transcribe: custom terms and hour-long files
Google details developer features for the Gemini 3.5 Transcribe speech-to-text model, supporting real-time streaming and batch file transcription.
Google↗
AUDIENCES
Voice system engineers
AI news and practical stories for this audience.
Latest stories
02GPT-Live-1 reaches the API at $0.05 per minute for voice
OpenAI's GPT-Live-1 API allows developers to build full-duplex voice agents capable of simultaneous listening and speaking with native handling of interruptions.
OpenAI↗