Minimized TTS Latency with Streaming and More in Cognigy.AI v4.71

Cognigy.AI v4.71 features Streaming support for ElevenLabs Text-to-Speech service to drastically reduce latency and enable instant audio responses by voice AI Agents.

Streaming TTS for Reduced Latency and Enhanced VUX

Traditional Text-to-Speech software waits for full text submission and processing before audio playback. With long bot utterances, these systems are conducive to noticeable latency that impacts seamless voice experiences.

Cutting-edge Streaming TTS technology now enables immediate speech generation by processing text inputs in real-time. Audio starts as soon as the initial words are processed, allowing for ongoing text receipt and simultaneous voice output.

Streaming TTS sets a new benchmark for real-time voice interactions by significantly lowering latency. It shines in two critical areas:

GenAI-Powered Voice Interactions: Leveraging LLMs in a controlled manner significantly enhances and personalizes customer interactions instantly. With Streaming TTS, AI Agents can return LLM-powered outputs as they are being produced.
Real-Time Translation on Voice: Streaming plays back audio responses concurrently with text translation, thereby minimizing voice RTT technical latency.

👉 See Voice RTT in Action

You can enable Streaming in the Voice Gateway Portal when configuring ElevenLabs as the STT service of choice.

Other Improvements

Cognigy.AI

Improved the Package Upload capability to resume on connection failure
Improved the default password policy for the organization to include a minimum of 1 special character and require a minimum length of 12 characters
Added new voices for text-to-speech for the Deepgram provider

Cognigy Insights

Moved the locale filters back to the additional filters panel
Improved by hiding the grain label in the widget's detailed view
Removed the redundant indent from the Transcript Explorer details
Changed the UI of the filters panel

For further information, check out our complete Release Notes here.