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

88%

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

82%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 strong, dense reference-style skill: executable examples for both REST and WebSocket paths, genuinely non-obvious gotchas, and layered pointers for deeper API detail. Remaining headroom is trimming minor redundancy, adding an explicit ordered workflow narrative, and moving inlined API detail into a reference file.

DimensionReasoningScore

Conciseness

The body is code-first and teaches only non-obvious SDK specifics (binary responses, lazy connection, custom client patch), but the opening line restates the description and the central-product-skills 'npx skills add' block is promotional padding that could be trimmed.

4 / 5

Actionability

Both quick starts are copy-paste-ready (REST generate call; full WS flow of createConnection, on('message'), connect, waitForOpen, sendText, sendFlush), backed by exact binary-response methods, named example files, and a parameter list.

5 / 5

Workflow Clarity

Each flow's sequence is concrete in code and Gotcha 3 makes ordering explicit ('createConnection() is lazy. Register handlers, then call connect() and waitForOpen()'), but there is no explicit end-to-end ordered narrative or error-recovery checkpoint.

4 / 5

Progressive Disclosure

No bundle files exist, and the body is well-sectioned with a clearly signaled layered reference section (in-repo reference.md/src paths, OpenAPI/AsyncAPI, Context7, product docs); however, the full parameter list and gotcha detail are inlined rather than split into reference files.

4 / 5

Total

17

/

20

Passed

Description

95%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.

An exemplary description: it states a precise scope with named SDK methods, gives both a 'Use when' clause and a six-term trigger list, and explicitly routes the adjacent voice-agent use case elsewhere. Only minor headroom exists on action-level specificity.

DimensionReasoningScore

Specificity

Names concrete API surfaces ('client.speak.v1.audio.generate' for one-shot REST, 'client.speak.v1.createConnection() / connect()' for streaming WebSocket) and scopes to JavaScript/TypeScript in this repo, but describes scope rather than a comprehensive list of actions Claude performs.

4 / 5

Completeness

Explicitly answers what ('Covers one-shot REST via client.speak.v1.audio.generate and streaming WebSocket via client.speak.v1.createConnection()') and when ('Use when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram Text-to-Speech v1'), with concrete trigger phrases.

5 / 5

Trigger Term Quality

The explicit trigger list ('TTS', 'text to speech', 'speak', 'aura', 'streaming TTS', 'speak.v1') covers natural synonyms and the model-family name a user would actually say; only 'speech synthesis' is absent.

5 / 5

Distinctiveness Conflict Risk

It carves a clear niche (Deepgram TTS v1 in this JS SDK) and actively disambiguates the nearest neighbor ('Use deepgram-js-voice-agent when you need full-duplex STT + LLM + TTS instead of one-way synthesis'), minimizing wrong-skill triggering.

5 / 5

Total

19

/

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.

Validation — 16 / 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.