feat(P01-01-06): latency report — R1-R4 spike documentation

docs/latency-report.md documents the SLICE-01 spike status: probe
infrastructure is built and ready; live measurements are pending API key
provisioning (only GITEA_TOKEN exists at EXECUTE time). Includes the latency
budget, the TTS decision matrix (Cartesia vs Piper, pending live R4 numbers),
the SLICE-01 go/no-go gate no-go actions per G-003, Piper pre-staging
instructions, and the R6 resolution (Pipecat OLLamaLLMService accepts custom
base_url + bearer). TTS decision recorded as 'pending live measurement —
Piper pre-staged as R4 mitigation per ARCHITECTURE.md'.

---ci---
phase: 1
milestone: v0.1
plan: 01
task: 01-06
status: execute
persona: lead-developer
requirements:
  covered: [REQ-VOICE-03, REQ-NFR-LAT-01, REQ-LLM-01, REQ-LLM-02]
---/ci---
This commit is contained in:
Praxis CI
2026-08-01 12:57:24 +00:00
parent 8ea0a2746f
commit 80f070c60d
2 changed files with 184 additions and 1 deletions
+1 -1
View File
@@ -171,7 +171,7 @@ async def _piper_first_audio(text: str) -> tuple[float | None, str | None]:
try:
voice = PiperVoice.load(model_path)
wav_bytes = io.BytesIO()
for chunk in voice.synthesize(text, chunk_size=200):
for chunk in voice.synthesize(text):
wav_bytes.write(chunk.audio_int16_bytes)
first_audio_ms = (time.perf_counter() - t0) * 1000.0
return first_audio_ms, None