azure-text-to-speech

Generate neural narration audio using Azure AI Speech (REST text-to-speech). Use when synthesizing voiceovers or narration in OpenMontage. Optional cloud TTS provider — preferred when AZURE_SPEECH_KEY is configured; the local piper_tts remains the default offline path. Shares one Speech resource with azure_stt.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/azure-text-to-speech/SKILL.md

Quality

Content

75%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable single-purpose skill body with concrete code, parameters, and a sensible verification step for batch generation. It is slightly verbose in its opening framing and could push detail (voice catalog, pricing) into reference files, but is broadly effective.

Suggestions

Trim the opening paragraph's restatement of the optional-provider/piper_tts/elevenlabs framing since the description already covers it; lead with the endpoint and capability instead.

Collapse the repetitive 'Using it in a pipeline' fallback chain prose into a one-line chain and move the voice alias table to a references file to keep SKILL.md as an overview.

Format the setup → route → verify → batch flow as an explicit numbered workflow with the 'listen to first segment before batch' checkpoint called out as a validation step.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and assumes competence, but the opening paragraph re-states the optional-provider/piper_tts-default/elevenlabs-cloning framing already present in the description, adding mild redundancy.	4 / 5
Actionability	Provides a concrete executable registry/execute code block, a voice alias table, and specific param values (rate "-4%" to "-8%", output formats), with only minor gaps such as reliance on the internal registry._tools accessor.	4 / 5
Workflow Clarity	Setup, routing, fallback chain, and a verification checkpoint ("listen to the first generated segment before batch-running a full script") are present and clearly ordered, though not formatted as an explicit numbered sequence.	4 / 5
Progressive Disclosure	Well-organized into clearly headed sections with only external doc links (no nested bundle references), but content like the full voice table and pricing detail lives inline where a reference file could carry it for a longer skill.	4 / 5
	Total	16 / 20 Passed

Description

82%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A tight, third-person description that clearly states the capability and its trigger conditions while carving out a distinct niche from sibling TTS/STT skills. The only weakness is that it lists a single concrete action rather than enumerating the range of things it can do.

Dimension	Reasoning	Score
Specificity	Names the domain and one concrete action ("Generate neural narration audio using Azure AI Speech (REST text-to-speech)"), but offers only a single primary action rather than a comprehensive list of capabilities.	3 / 5
Completeness	It explicitly answers both what ("Generate neural narration audio using Azure AI Speech") and when ("Use when synthesizing voiceovers or narration in OpenMontage") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural trigger phrases like "synthesizing voiceovers or narration" and "text-to-speech"/"TTS" appear, giving good keyword coverage, though a few common synonyms (e.g. "speech", "dubbing") are absent.	4 / 5
Distinctiveness Conflict Risk	The Azure Speech TTS niche is sharply scoped and explicitly contrasted against piper_tts, elevenlabs_tts, and azure_stt, minimizing overlap with sibling skills.	5 / 5
	Total	17 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: calesthio/OpenMontage
Path: .agents/skills/azure-text-to-speech/SKILL.md
Commit: 08e2151

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.