Generate natural speech from text in any language

Converts written content into audio using multiple TTS engines — Inworld (100+ languages, emotion control), ElevenLabs (premium voices), and others — with low-latency options for real-time use.

Best for: Founders building voice features into products or creating multilingual audio content at scale.

Engineering / pipelines-dataatomicfor-foundersneeds-integrationfrom-text

Source

Creator's repository · inference-sh/skills

View on GitHub