//
Busque em todas as páginas da documentação
7 pages in this section.
The complementary speech-to-text and text-to-speech API pair - how Transcribe and Polly cover opposite directions of the same voice pipeline.
Transcribe a short audio file and synthesize speech from text via SDK - six starter examples across both services in Python (boto3) and TypeScript (AWS SDK v3).
Batch job submission vs real-time streaming transcription via SDK - two conceptually different APIs for two different audio problems.
Controlling synthesized speech prosody and timing via SDK - choosing voices and engines, shaping speech with SSML, and getting timing metadata with speech marks.
Audio format handling and cost-aware job sizing - a checklist for calling Transcribe and Polly from the SDK, across boto3 and AWS SDK v3.