Led · Voice Runtime·VoiceTTSMigrationLatency

Local Voice Infrastructure Migration

Moving voice generation from cloud cost to local speed.

A migration from cloud-hosted voice models to local inference, keeping voice quality while improving speed, cost, and multilingual flexibility.

cloud migrationLocal
runtime costLower
response goalFaster
language outputMulti

The Problem

The original cloud voice stack had strong quality but created cost, latency, and language constraints. It could output Chinese well, but could not flex into multilingual character performance with the same voice identity.

Role: Architecture Planner · Adapter Implementer · API Compatibility Owner · Rollout Lead

Cloud → Local

Cloud voice stack

Quality was good but locked to Chinese, with per-usage cost and network latency.

cost
latency
Chinese onlyPer-usage costNetwork latency

Local inference

Same voice identity across languages, faster and cheaper to run.

speed
languages
RuntimeCloud-hostedLocal inference
CostPer-usageNo usage fee
LatencyNetwork round-tripNear-runtime
LanguagesChinese onlyMultilingual identity

Contributions

What I actually did.

01

Planned the migration architecture from cloud to local runtime.

02

Adjusted interfaces and compatibility layers around the existing API contract.

03

Handled speaker mapping, latency constraints, quality checks, and rollout planning.

04

Owned the migration work outside the voice model training and behavior tuning itself.

AI collaboration governance

Picking the right model out of dozens of open-source ones wasn't me listening one by one on a hunch — it's that I designed "how to evaluate" into a pipeline the AI runs itself. This page is how I governed a large-scale model selection.

Governance cases

Open for first-hand evidence

The AI's ingrained pattern

Voice quality is inherently subjective: whether the emotional range is enough, whether the Taiwanese accent is authentic — auditioning one by one is slow and inconsistent, and across dozens of open-source models simply can't be compared reliably. Exactly where AI collaboration most easily degrades into "gut feel."

The governance mechanism I built

Orchestrated multiple sub-agents to build an automated evaluation pipeline, decomposing subjective audio judgment into cross-verifiable metrics and running a consistent comparison across dozens of models — not resting on my ears alone.

The collaboration value it unlocked

Made "preserving rich emotional range and tunability under severely limited local compute" an executable engineering process; the final model was what the pipeline surfaced, not a gut pick.

The AI's ingrained pattern

When swapping the underlying inference engine, AI tends to only care that "the new one runs," ignoring the pile of downstream dependencies on the old API contract, speaker mapping, and latency assumptions — one change and the whole chain blows up.

The governance mechanism I built

Constrained the migration around the existing API contract: added a compatibility layer, explicitly handled speaker mapping and latency limits, and planned a phased rollout, so the backend moved from cloud to local while staying invisible to the layers above.

The collaboration value it unlocked

Seven voice lines' cloud cost dropped from ~NT$90k/month to nearly zero, while the upper system didn't need a rewrite for this migration — cost cut without paying in stability.

Outcomes

01

Cost reduced

Local inference removed the cloud usage dependency for the voice runtime.

02

Latency improved

Moving generation closer to the runtime improved responsiveness for interactive character use.

03

Multilingual voice identity

The local model can preserve the same character voice across languages, expanding use cases beyond the original Chinese-only output.