sherpa-onnx-tts

Local text-to-speech via sherpa-onnx (offline, no cloud)

1.51x

Quality

56%

Does it follow best practices?

Impact

100%

1.51x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./openclaw/skills/sherpa-onnx-tts/SKILL.md

Evaluation results

100%

56%

Batch Audio Preview Generator

CLI wrapper usage and env var configuration

Criteria

Without context

With context

SHERPA_ONNX_RUNTIME_DIR usage

100%

SHERPA_ONNX_MODEL_DIR usage

100%

Output flag -o

100%

Correct command name

100%

Sequential naming

100%

Blank line skipping

100%

Output subdirectory

100%

No hardcoded paths

100%

README env configuration

100%

PATH or baseDir invocation

100%

Without context: $0.2910 · 1m 8s · 20 turns · 27 in / 3,663 out tokens

With context: $0.5192 · 1m 38s · 28 turns · 32 in / 5,761 out tokens

100%

31%

Voice Model Onboarding Setup

Multi-model configuration and openclaw.json setup

Criteria

Without context

With context

openclaw.json path

100%

skills.entries key

20%

100%

SHERPA_ONNX_RUNTIME_DIR in config

100%

SHERPA_ONNX_MODEL_DIR in config

25%

100%

Runtime install path

100%

Models install path

100%

Model file flag

100%

Tokens file override

66%

100%

Output flag usage

60%

100%

Voice-parameterized path

100%

Without context: $0.3057 · 1m 19s · 16 turns · 21 in / 5,087 out tokens

With context: $0.5384 · 2m 2s · 22 turns · 27 in / 7,498 out tokens

100%

14%

Cross-Platform TTS Helper Module

Cross-platform binary invocation and library path setup

Criteria

Without context

With context

Correct binary name

100%

Binary in bin/ subdir

100%

.exe on Windows

50%

100%

LD_LIBRARY_PATH on Linux

100%

DYLD_LIBRARY_PATH on macOS

100%

PATH extension on Windows

100%

lib/ directory used

100%

--vits-model flag

100%

--vits-tokens flag

100%

--vits-data-dir flag

100%

--output-filename flag

100%

Without context: $0.2510 · 1m 15s · 14 turns · 20 in / 4,975 out tokens

With context: $0.4879 · 1m 41s · 22 turns · 27 in / 6,381 out tokens

Repository: trpc-group/trpc-agent-go
Commit: 8763418

Evaluated: 16 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Batch Audio Preview Generator Voice Model Onboarding Setup Cross-Platform TTS Helper Module

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.