All tags
Topic: "voice-activity-detection"
Promptable Prosody, SOTA ASR, and Semantic VAD: OpenAI revamps Voice AI
gpt-4o-transcribe gpt-4o-mini-tts o1-pro kokoro-82m openai replicate speech-to-text text-to-speech voice-activity-detection prompt-engineering real-time-processing model-release api function-calling structured-outputs model-performance juberti sama reach_vb kevinweil omarsar0
OpenAI has launched three new state-of-the-art audio models in their API, including gpt-4o-transcribe, a speech-to-text model outperforming Whisper, and gpt-4o-mini-tts, a text-to-speech model with promptable prosody allowing control over timing and emotion. The Agents SDK now supports audio, enabling voice agents. OpenAI also updated turn detection for real-time voice activity detection (VAD) based on speech content. Additionally, OpenAI's o1-pro model is available to select developers with advanced features like vision and function calling, though at higher compute costs. The community shows strong enthusiasm for these audio advancements, with a radio contest for TTS creations underway. Meanwhile, Kokoro-82M v1.0 emerges as a leading open weights TTS model with competitive pricing on Replicate.
OpenAI Realtime API and other Dev Day Goodies
gpt-4o-realtime-preview gpt-4o openai livekit agora twilio grab automat voice-activity-detection function-calling ephemeral-sessions auto-truncation vision-fine-tuning model-distillation prompt-caching audio-processing
OpenAI launched the gpt-4o-realtime-preview Realtime API featuring text and audio token processing with pricing details and future plans including vision and video support. The API supports voice activity detection modes, function calling, and ephemeral sessions with auto-truncation for context limits. Partnerships with LiveKit, Agora, and Twilio enhance audio components and AI virtual agent voice calls. Additionally, OpenAI introduced vision fine-tuning with only 100 examples improving mapping accuracy for Grab and RPA success for Automat. Model distillation and prompt caching features were also announced, including free eval inference for users opting to share data.