Kokoro-FastAPI is a Dockerized FastAPI service that turns text into speech using the Kokoro-82M model through an OpenAI-compatible API. It is used by developers and self-hosters who need multilingual, multi-speaker speech generation, captions, phonemes, or an optional web interface.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/remsky/kokoro-fastapi/integration-testsnpx skills add remsky/Kokoro-FastAPI --skill integration-testsgit clone --depth 1 https://github.com/remsky/Kokoro-FastAPIWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/remsky/kokoro-fastapi/integration-tests)<a href="https://agentmods.dev/skills/remsky/kokoro-fastapi/integration-tests"><img src="https://agentmods.dev/badge/skills/remsky/kokoro-fastapi/integration-tests.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00025 | $0.00307 |
| Opus 5 | $0.00013 | $0.00153 |
| Sonnet 5 | $0.00005 | $0.00061 |
| Haiku 4.5 | $0.00003 | $0.00031 |
Grade A, and why
integration-tests scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Integration tests
Prerequisites
A running Kokoro server (GPU or CPU container) on port 8880.
Running
Unit tests (no server needed):
uv run pytest
Integration tests use the prebuilt test-client image with Whisper baked in. Mount the test directory and point at the running server:
docker run --rm --network host ^
-v "%cd%/api/tests/integration:/tests/integration:ro" ^
-e KOKORO_BASE_URL=http://localhost:8880 ^
-e WHISPER_MODEL=/opt/whisper/small ^
ghcr.io/remsky/tts-api-test-client:latest
Or the full compose stack (builds a CPU server + test-client, self-contained):
docker compose -f docker/docker-compose.test.yml up --build ^
--abort-on-container-exit --exit-code-from test-client
What runs
test_rate_durations.py- speed/rate tag scaling against real audio durationstest_tts_roundtrip.py- synth + Whisper transcribe across 9 languages, WER/CER thresholdstest_voices_endpoint.py- voice listing shape, legacy compat, nova mapping
17 tests total. The roundtrip tests need ~30s (Whisper inference is the bottleneck).
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 38 lines · 25 tokens per session scan A 4c76b59c2f44
integration-tests is a skill published in the GitHub repository remsky/Kokoro-FastAPI (5,406 stars, last pushed 2d ago), licensed Apache-2.0. It adds 25 tokens to every session and 307 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
uat-testing
Run end-to-end User Acceptance Tests for Agent Brain features. Builds wheels, installs packages, starts a test server, runs tests, and reports results — all without permission prompts.
tracecat-qa
QA Tracecat product features in a real local cluster. Use for QA, browser tests, smoke tests, or manual verification of Tracecat UI flows and PR changes with just cluster. In Codex desktop app sessions, use browser:control-in-app-browser first; use Chrome DevTools only after the in-app browser path concretely fails or…
lgtest
When the user invokes "LGTest", reviews the most recent changes (especially from the current chat, but not limited to it) and proposes adding new tests—unit, UI, smoke, API, or integration—as appropriate. Use when the user says "LGTest" or asks to review changes and propose tests.
测试基础设施
提供端到端测试所需的基础能力脚本，包括日志拦截提取、数据库快照对比、副作用 mock 和验证。.
test-generation
Generate a test strategy and starter test stubs for given modules across unit, integration, and e2e layers (pytest/jest/playwright). Trigger on: generate tests, test plan, test strategy, coverage plan, test scaffolding.
agent-qa
End-to-end QA testing for Agent2 agents. Starts the agent service, sends real API requests from eval datasets, validates responses against the output schema, and generates a health report with confidence stats. Use when asked to "test this agent", "QA the agent", "does this agent work", or "run agent health check".