CtrlK
BlogDocsLog inGet started
Tessl Logo

deepgram-js-text-to-speech

Use when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram Text-to-Speech v1 (`/v1/speak`) for audio synthesis. Covers one-shot REST via `client.speak.v1.audio.generate` and streaming WebSocket via `client.speak.v1.createConnection()` / `connect()`. Use `deepgram-js-voice-agent` when you need full-duplex STT + LLM + TTS instead of one-way synthesis. Triggers include "TTS", "text to speech", "speak", "aura", "streaming TTS", and "speak.v1".

72

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

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-organized, actionable body with executable REST and WSS examples, a clear parameter surface, layered external references, and a strong Gotchas checklist. It is efficient and assumes Claude's competence, with only minor density and edge-case gaps.

Suggestions

Add a one-line note on auth/env failure and on Flush-before-close ordering in the WSS quick start to close the actionability gap.

Collapse the layered 'API reference' URL list into a compact table or shorter bullet list to improve conciseness and scanability.

Consider extracting the full parameter surface and server-event list into a bundled reference file so the body stays a true overview (improves progressive_disclosure toward 5).

DimensionReasoningScore

Conciseness

Lean body that jumps to executable code and a parameter surface list without explaining what TTS or WebSockets are; only minor extras (the 'Central product skills' promotion and a slightly dense URL list) keep it from a 5.

4 / 5

Actionability

Provides copy-paste-ready code for both REST generate and WSS streaming with real method calls and a binary-response pointer, plus an enumerated parameter surface; a few edge-case gaps (auth errors, flush/close ordering) prevent a 5.

4 / 5

Workflow Clarity

Quick-start sections are clearly sequenced (auth → REST/WSS) and the Gotchas list acts as a pitfall checklist; not a destructive/batch workflow so no validate→fix→retry loop is required, but explicit checkpoints are absent.

4 / 5

Progressive Disclosure

Well-sectioned overview that delegates bulk detail to one-level-deep references (`reference.md`, `examples/*.ts`, canonical OpenAPI/AsyncAPI URLs, Context7 ID); only the dense layered-URL list and absence of bundle files keep it from a 5.

4 / 5

Total

16

/

20

Passed

Description

100%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 strong, third-person description that states concrete capabilities, enumerates natural trigger terms, answers both what and when, and explicitly routes to a sibling skill to avoid conflicts. Voice and trigger phrasing are consistent with rubric guidance.

DimensionReasoningScore

Specificity

Names the domain (Deepgram TTS v1 `/v1/speak`) plus concrete methods for both one-shot REST (`client.speak.v1.audio.generate`) and streaming WSS (`createConnection()`/`connect()`), giving comprehensive coverage of the API surface.

5 / 5

Completeness

Clearly answers both 'what' (audio synthesis via REST/WSS) and 'when' (writing/reviewing JS/TS calling `/v1/speak`), with concrete trigger phrases and a routing cue to a sibling skill.

5 / 5

Trigger Term Quality

Explicitly lists natural triggers — 'TTS', 'text to speech', 'speak', 'aura', 'streaming TTS', 'speak.v1' — covering synonyms, abbreviations, and technical variants users would actually say.

5 / 5

Distinctiveness Conflict Risk

Explicitly differentiates one-way synthesis from full-duplex `deepgram-js-voice-agent` (STT + LLM + TTS), carving a clear niche with minimal trigger overlap.

5 / 5

Total

20

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
deepgram/deepgram-js-sdk
Reviewed

Table of Contents

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.