Over 500 developers registered for our Open Source Realtime AI Hackathon. We're excited to share blog posts from a weekend of hacking and developer community. To kick it off, we're thrilled to share a conversation with Christoph Heike won first place in our Open Source Conversational & Multi-modal AI Hackathon, which took place from October 19 to 20 in San Francisco. This two-day event, sponsored by Pipecat, Daily, Google Cloud, Oracle Cloud, Cartesia, COVAL, Product Hunt, Tavus, and VAPI gat
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
Build voice-to-voice AI agents that directly use your Twilio numbers, Twilio Flex, Twilio Studio, and Twilio WebSockets, for both dial-in and dial-out
Voice-to-Voice AI with any LLM, leveraging Open Source SDKs