Clause-by-clause streaming TTS

Replies are spoken clause by clause as they are generated.

IMPLEMENTED , rung 2 of 8 Recorded 2 August 2026

Technical

What it is

Clause-chunked streaming TTS over a WebSocket streaming endpoint.

Truth ladder

Rung 2 of 8: IMPLEMENTED

Code exists. Nothing has demonstrated that it behaves correctly.

Qualified as PARTIAL: part of this capability is not at the rung shown.

Project record: IMPLEMENTED

CONCEPT Designed or specified. No working code yet.
IMPLEMENTED Code exists. Nothing has demonstrated that it behaves correctly.
TESTED Automated tests exercise it in isolation, often against fixtures.
INTEGRATED Wired into the rest of JARVIS and tested across component boundaries.
PRODUCTION-REACHABLE The owner can reach it through the real runtime path, not only through a test harness.
LIVE-PROVEN A bounded probe ran the real code path on a booted JARVIS on the real machine and recorded evidence. The project treats live evidence as expiring after 24 hours, so every live reading here shows the date it was taken.
FORMALLY VERIFIED Its critical property is checked by a proof or exhaustive verification.
RELEASE-QUALIFIED Passed every qualification gate for a named release.

Limits

Registry state IMPLEMENTED set 2026-08-02. Probe FAILED its latency budget: measured warm first-chunk p50 288.6 ms / p95 367.5 ms over 64 real syntheses against a 220 ms p95 budget (recorded 2026-08-02).

Record

Only states recorded in the public export are listed. Earlier states may exist in the project’s private ledgers.

Connected work

Neighbours