Tue Jul 22 2025
You don’t need a WebRTC server for your voice agentsWhen to use cloud vs serverless WebRTC, for voice agents and conversational AI.
Jumpstart development with Daily
Audio SDK
We carefully develop APIs to be simple and streamlined, making it easy to add great audio to your product.
Music playback
Select music or voice modes for audio, or take low-level control and customize bitrates and audio processing.
Krisp AI-powered voice
Krisp’s advanced noise cancellation technology uses AI to eliminate background noise, making clear conversations possible in any environment.
Audio recording
Record audio sessions locally or in the cloud, or send raw tracks directly to your S3 bucket.
Audio streaming
Reach millions by streaming your rooms over HLS or RTMP, all with one line of code.
Spatial audio
Build spatial audio experiences. Selectively subscribe to tracks, adjust volume levels based on proximity, and integrate audio into 3D worlds.
Transcription and AI
Daily’s APIs provide easy integration with hosted AI services, LLMs, and proprietary ML infrastructure. Standard AI features include transcription and noise cancellation.
Raw track access
Access raw audio tracks to implement your own pre- or post-processing.
[BLOG]
From the blog
Fri Jul 18 2025
Smart Turn v2: faster inference, and 13 new languages for voice AIBuild voice agents with accurate turn detection. Open source, native audio semantic VAD.
Tue Jun 24 2025
Advice on Building Voice AI in June 2025My top three pieces of advice for people getting started with voice agents. 1. Spend time up front understanding why latency and instruction following accuracy drive voice AI tech choices. 2. You will need to add significant tooling complexity as you go from proof of concept to production. Prepare for that. Especially important: build lightweight evals as early as you can. 3. The right path is: start with a proven, "best practices" tech stack -> get everything working one piece at a time ->