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

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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 skill body with executable examples for both REST and WebSocket TTS and accurate file references. It is slightly verbose in its catalog sections and lacks explicit validation checkpoints for the streaming connection, though the task is low-risk.

Suggestions

Add a brief connection-health checkpoint to the WebSocket quick start (e.g. handling a non-opening socket or a missing Flushed event before closing) to strengthen workflow clarity.

Tighten the 'Key parameters / API surface' and layered 'API reference' lists into pointers to reference.md and the canonical OpenAPI/AsyncAPI URLs rather than inline catalogs, improving conciseness.

Consider moving the seven-item Gotchas list into reference.md with a short top-line summary here to reduce inline token cost.

DimensionReasoningScore

Conciseness

Largely lean and assumes Claude's competence, but sections like the full Key parameters list, the layered API reference, and the gotchas include some catalog-style enumeration that could be tightened or delegated to references.

2 / 3

Actionability

Provides copy-paste-ready executable code for both REST and WebSocket paths, cites exact source/example files, and enumerates concrete API surfaces (`sendText`, `sendFlush`, `response.arrayBuffer()`) rather than pseudocode.

3 / 3

Workflow Clarity

Quick-start sequences are present (register handlers, connect, waitForOpen, sendText, sendFlush), but there is no validation/checkpoint guidance for confirming audio was received or handling a failed/stalled connection; this TTS use is non-destructive so the cap is soft.

2 / 3

Progressive Disclosure

SKILL.md acts as an overview with one-level-deep pointers (reference.md, real example files, src/ paths, canonical OpenAPI/AsyncAPI URLs), and no references/, scripts/, or assets/ bundle exists to nest further; structure is clear and navigable.

3 / 3

Total

10

/

12

Passed

Description

100%

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, specific description: it names concrete SDK methods, answers both what and when with explicit triggers, and actively disambiguates from the related voice-agent skill. It is written in third person and avoids fluff.

DimensionReasoningScore

Specificity

Names concrete SDK methods (`client.speak.v1.audio.generate`, `createConnection()`, `connect()`) and both REST and WebSocket surfaces, listing multiple specific actions rather than vague language.

3 / 3

Completeness

Explicitly answers both what (one-shot REST + streaming WebSocket TTS via the SDK) and when ("Use when writing or reviewing JavaScript/TypeScript... that calls Deepgram Text-to-Speech v1"), with explicit trigger guidance.

3 / 3

Trigger Term Quality

Lists natural terms a user would say ("TTS", "text to speech", "speak", "aura", "streaming TTS") plus the technical "speak.v1"; good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

Scoped to JS/TS in this repo for one-way TTS and explicitly redirects full-duplex STT+LLM+TTS to `deepgram-js-voice-agent`, giving it a clear niche unlikely to trigger the wrong skill.

3 / 3

Total

12

/

12

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.