A diagnostic command for claude-tts, a text-to-speech system that turns written text into audio. It checks the installation, background process, audio connection, Python packages, speech backend, and summarizer limits.

Run it when setting up claude-tts or troubleshooting disk space, a stopped service, a missing connection, missing packages, or an unreachable speech service.

It helps identify why speech generation is unavailable or unreliable and gives one suggested fix for each warning.

tts:doctor — Command for Claude Code by chendrizzy

Install

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.

Clone the repo

git clone --depth 1 https://github.com/chendrizzy/claude-tts

Made for: Claude Code.

Or install claude-tts, the plugin that ships this one along with the rest of its 1 skill, 8 commands, 5 hooks.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/chendrizzy/claude-tts/doctor/github.svg)](https://agentmods.dev/commands/chendrizzy/claude-tts/doctor)

Your own site

<a href="https://agentmods.dev/commands/chendrizzy/claude-tts/doctor"><img src="https://agentmods.dev/badge/commands/chendrizzy/claude-tts/doctor/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/chendrizzy/claude-tts/doctor"><img src="https://agentmods.dev/badge/commands/chendrizzy/claude-tts/doctor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 671 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00042	$0.00671
Opus 5	$0.00021	$0.00336
Sonnet 5	$0.00008	$0.00134
Haiku 4.5	$0.00004	$0.00067

Measured 8d ago against content hash 618b87128754, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

tts:doctor 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 8d 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.

commands/doctor.md · 43 lines

What it actually says

Diagnose the claude-tts installation. This command is idempotent — safe to run anytime, changes nothing. For each check print PASS or WARN and, on WARN, exactly one remediation.

Checks:

Disk — free space on the volume holding the audio temp directory. WARN if low; below ~200 MB free the daemon's disk guard evicts cache, refuses to synthesize, and fires a loud desktop + statusline alert (it no longer silently mutes).
Daemon process + socket — is the daemon process alive AND is the socket bound at ${CLAUDE_TTS_SOCKET:-${XDG_RUNTIME_DIR:-/tmp}/claude-tts.sock}? WARN if the process is up but the socket is missing (a stale/orphaned daemon), with a restart remediation.
Python deps — are the daemon's required Python packages importable in its environment? WARN with the install command if any are missing.
Backend reachability — for the configured backend, confirm it is reachable: Ollama responding, the Voicebox app running, or edge-tts network access. WARN with how to start/restore the backend.
Summarizer budget vs. inner timeout (Ollama LLM path only) — read summarizer.soft_tokens (default 200) and slack_tokens (default 96) → the hard generation ceiling num_predict = soft + slack (default 296), and summarizer.inner_timeout_s (default 5.0). A full-budget summary must finish within the inner timeout or it falls back to the deterministic rule-based summary. If Ollama is reachable, time a small generation (num_predict: 64) against the configured model and derive tokens/sec from the response's eval_count / eval_duration; WARN if inner_timeout_s < (num_predict / tok_per_sec) × 1.3 (a full-budget summary risks timing out) — remediation: raise inner_timeout_s, or lower soft_tokens / slack_tokens. Report the numbers either way (e.g. "budget 296 tok ≈ 1.9 s at ~155 tok/s vs 5.0 s timeout — OK"). The bundled defaults pass with margin at normal speeds; this mainly catches a budget raised past its timeout, or a host too slow for the configured budget. If throughput can't be measured, only WARN when the budget exceeds 296 while the timeout is still ≤ 5.0 s.

After all checks, print a one-line overall verdict (all PASS, or the count of WARNs). Do not hardcode absolute personal paths; read locations from ~/.config/claude-tts and the XDG socket expression above.

Changes

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.

8d ago First seen · 43 lines · 42 tokens per session scan A 618b87128754

Subscribe to this mod's changes

tts:doctor is a command published in the GitHub repository chendrizzy/claude-tts (1 stars, last pushed 22d ago), licensed MIT. It adds 42 tokens to every session and 671 once invoked, about $0.0002 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 2026-08-31.

Claude Code Debugging accessibility ai-agent claude-code-plugin kokoro local-llm

tts:doctor

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

wp-debug

debug-helper

error-handling-specialist

linkerd

wp-tailwindify

ia-report-bug