deepgram-java-text-to-speech
Use when writing or reviewing Java code 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 synthesis via `client.speak().v1().v1WebSocket()`. Use `deepgram-java-voice-agent` for full-duplex assistants instead of one-way synthesis. Triggers include "tts", "text to speech", "speak", "aura", "streaming tts", and "speak websocket".
89
86%
Does it follow best practices?
Impact
Pending
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 clearly defines its scope (Deepgram TTS v1 in Java), lists concrete API methods and patterns, provides explicit trigger terms, and proactively distinguishes itself from a related skill. It follows best practices by using third person voice and including both 'Use when' guidance and boundary conditions.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: one-shot REST audio generation via a specific method path, streaming synthesis via WebSocket, and distinguishes from full-duplex assistants. Includes specific API paths and method signatures. | 3 / 3 |
Completeness | Clearly answers both 'what' (calling Deepgram TTS v1 for one-shot REST and streaming synthesis in Java) and 'when' (explicit 'Use when' clause at the start, plus explicit trigger terms listed). Also includes a boundary condition distinguishing from the voice-agent skill. | 3 / 3 |
Trigger Term Quality | Explicitly lists natural trigger terms ('tts', 'text to speech', 'speak', 'aura', 'streaming tts', 'speak websocket') and includes technical terms users would naturally use like '/v1/speak', 'audio synthesis', and 'Deepgram Text-to-Speech'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive: scoped to Java code, Deepgram TTS v1 specifically, and explicitly differentiates from the `deepgram-java-voice-agent` skill for full-duplex assistants, reducing conflict risk with related skills. | 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 strong, actionable skill with executable Java code examples covering both REST and WebSocket TTS paths. Its main weakness is the lack of validation/error-handling checkpoints in the workflows (e.g., verifying audio output, handling connection timeouts) and some minor verbosity in the gotchas and promotional sections. The progressive disclosure and API surface coverage are excellent.
Suggestions
Add explicit validation steps after generating audio (e.g., check file size > 0, verify audio headers) to improve workflow clarity for production use.
Trim the 'Central product skills' section to a single line or move it to a separate onboarding doc — it doesn't help Claude perform TTS tasks.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but has some unnecessary elements: the 'Central product skills' section at the bottom is promotional/contextual rather than instructional, the 'There is no Java TextBuilder helper' gotcha explains something that doesn't exist (negative knowledge of limited value), and some import lists are verbose. However, most content earns its place. | 2 / 3 |
Actionability | Provides fully executable, copy-paste-ready Java code for both REST and WebSocket paths, including proper imports, error handling in callbacks, and async equivalents. The API surface section gives concrete method signatures and parameter names. | 3 / 3 |
Workflow Clarity | The REST and WebSocket workflows are clear sequences, and the WebSocket example correctly shows flush-before-close ordering. However, there are no explicit validation checkpoints — no guidance on verifying the output file is valid audio, checking for errors in the InputStream, or handling connection failures beyond the happy path. | 2 / 3 |
Progressive Disclosure | Content is well-structured with clear sections progressing from authentication → quick starts → async → parameters → API references → gotchas. The layered API reference section provides well-signaled one-level-deep pointers to in-repo source, OpenAPI specs, and product docs. Even without bundle files, the organization is clean and navigable. | 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-java-sdk
- Commit
de2dd4b
- 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.