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".
71
86%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
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.
This is an excellent skill description that hits all the marks: it specifies concrete API methods and endpoints, provides explicit 'Use when' guidance with natural trigger terms, and even disambiguates from a related skill. The description is concise yet comprehensive, making it easy for Claude to select the right skill from a large pool.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: one-shot REST via `client.speak.v1.audio.generate`, streaming WebSocket via `client.speak.v1.createConnection()` / `connect()`, and references the specific API endpoint `/v1/speak`. Very concrete and actionable. | 3 / 3 |
Completeness | Clearly answers both 'what' (Deepgram TTS v1 audio synthesis via REST and WebSocket) and 'when' (explicit 'Use when' clause at the start, plus explicit trigger terms). Also includes a disambiguation clause pointing to a different skill for full-duplex scenarios. | 3 / 3 |
Trigger Term Quality | Explicitly lists natural trigger terms: 'TTS', 'text to speech', 'speak', 'aura', 'streaming TTS', and 'speak.v1'. These cover common user phrasings and product-specific terms well. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific API paths, method names, and an explicit disambiguation from the related `deepgram-js-voice-agent` skill. The niche is clearly scoped to one-way TTS synthesis via Deepgram's JS SDK, making conflicts unlikely. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill that provides concrete code examples for both REST and WebSocket TTS paths. Its main weakness is the lack of error handling/validation steps in the WebSocket workflow and some minor verbosity in peripheral sections. The gotchas section is a strong differentiator that captures non-obvious SDK-specific knowledge.
Suggestions
Add error handling and validation checkpoints to the WebSocket workflow (e.g., handling connection errors from `connect()`, checking `waitForOpen()` timeout, verifying audio payload type before processing).
Trim the 'Central product skills' section to 1-2 lines or move it to a footer — it's tangential to the TTS task and consumes tokens.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some unnecessary explanation (e.g., the 'Central product skills' section at the bottom, the 'When to use this product' section partially restates what Claude could infer). The gotchas section is valuable but a couple items border on obvious. Overall mostly lean but could be tightened. | 2 / 3 |
Actionability | Provides fully executable, copy-paste-ready code examples for both REST and WebSocket paths, with specific method names, event types, and structured message formats. The gotchas section adds concrete, specific guidance that prevents real mistakes. | 3 / 3 |
Workflow Clarity | The REST path is a single call and is clear. The WebSocket path shows the correct sequence (create → register handlers → connect → waitForOpen → sendText → sendFlush) but lacks explicit validation/error-handling checkpoints. For WebSocket operations where connection failures and audio payload mismatches are common, there are no feedback loops or error recovery steps mentioned. | 2 / 3 |
Progressive Disclosure | Well-structured with clear sections progressing from overview to quick starts to detailed parameters. References to example files, in-repo source paths, external API docs, and the central skills bundle are clearly signaled and one level deep. Navigation is easy and content is appropriately split. | 3 / 3 |
Total | 10 / 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- deepgram/deepgram-js-sdk
- Commit
bcffba7
- 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.