AWS publishes two guides on sentence-level streaming of Kokoro-82M TTS on SageMaker AI and setting autoscaling from measurements
Announced October 22, 2026
Verified (fact)
To reduce response latency for voice agents, AWS described sending each sentence to Kokoro-82M for speech synthesis as soon as the agent produces it, and returning audio to the browser via Server-Sent Events or a unified binary transport. A separate post explains how to measure two values, Q_max and T_total, on a Kokoro-82M endpoint deployed in a custom container and derive an autoscaling policy from them.
Why it matters (interpretation)
It is a practical reference that addresses both perceived latency and GPU cost in TTS serving.
Sources
More about AWS
-
Amazon Polly Generative engine gets major upgrade: more expressive and accurate, 14 new voices in 9 locales, Hindi and Finnish GA
AWS upgraded the Generative engine of Amazon Polly to produce more expressive and accurate speech with low latency. It added 14 new...
-
AWS publishes guide to deploying AI agents with Amazon Quick in HIPAA-covered environments
AWS noted that Amazon Quick is a HIPAA-eligible service but that eligibility and compliance are separate, and laid out who is covered by...
-
AWS makes SageMaker AI 'training sessions' generally available, letting users write post-training loops without managing GPUs
AWS has added a 'training sessions' feature to SageMaker AI's serverless model customization and made it generally available. Users...
-
AWS shows how to build AAIF, an agent framework that sends simple tasks to local SLMs and complex requests to Bedrock
AWS introduced the Adaptive Agentic Intelligence Framework (AAIF), built with Strands Agents. Routine tasks are handled by a local small...
-
AWS outlines three ways to train Qwen3 on Trainium with torchtitan
AWS laid out three ways to train Qwen3 with torchtitan on a single trn2.48xlarge instance. The paths use the Hugging Face Transformers...