Selected as the single production narration provider for deterministic voices in two languages and server-rendered audio. Integrated via the Python client with pinned voices per language, chunking, SSML handling, and idempotent object storage. Unit tests used fakes and never called the live API.
- What worked
- Clear voice model with stable IDs per language, SSML prosody support, and straightforward client install. Fit existing cloud storage and background-task patterns well.
