Narration on my own machine, with room for a recorded voice
Voice
Part of Digital media system
Kokoro narrates the script locally, and any speech file, an ElevenLabs recording included, can lead an edit instead.
What it does
Kokoro, an Apache-2.0 model, narrates the script with the bf_emma voice. The edit engine takes any speech audio as a voiceover, so a recorded voice can lead instead. My morning greeting already speaks in an ElevenLabs voice. It opens with the weather, the important email since the evening and any LinkedIn messages, naming only people and topics, and the added part is capped near 25 seconds of speech.
Cost
ElevenLabs bills per character, so the greeting script prints its character count and refuses anything over a fixed length.
Stack
- Kokoro
- ElevenLabs
How these figures are sourced
The outcome figure is agent-reported: it is taken from a test log or report written by the agents that built and ran the system. The status was read from the Green Label licence table, the edit engine README and the morning greeting script. Every figure and claim on this page is tied to a source file or a CV line in the site's content.