CtrlK
BlogDocsLog inGet started
Tessl Logo

deepgram-python-text-to-speech

Use when writing or reviewing Python code in this repo that calls Deepgram Text-to-Speech v1 (`/v1/speak`) for audio synthesis. Covers one-shot REST (`client.speak.v1.audio.generate`) and streaming WebSocket (`client.speak.v1.connect`). Also covers the in-repo `deepgram.helpers.TextBuilder` for incremental text assembly before synthesis. Use `deepgram-python-voice-agent` when you need full-duplex STT + LLM + TTS with barge-in. Triggers include "TTS", "speak", "synthesize voice", "aura", "text to speech", "speak.v1", "TextBuilder".

80

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

100%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, code-first skill body with executable examples across REST, WSS, TextBuilder, and async paths, clear sequencing for the streaming workflow, and well-signaled external references. It respects the context window while remaining fully actionable.

DimensionReasoningScore

Conciseness

Lean body that assumes Claude's competence — it never explains what TTS or WebSockets are — and every section (auth, REST/WSS quick start, TextBuilder, async, params, gotchas) earns its place with non-obvious, actionable detail.

3 / 3

Actionability

Provides fully executable, copy-paste-ready code for REST, WSS streaming, TextBuilder, and async equivalents with real method calls and parameters, plus a concrete gotcha list.

3 / 3

Workflow Clarity

The WSS flow is explicitly sequenced (send_text → send_flush → send_close → start_listening) with blocking-mode caveats and a gotcha that flush-before-close prevents dropped trailing audio, giving clear checkpoints for the fragile streaming operation.

3 / 3

Progressive Disclosure

Single-file skill with well-organized sections that point one level deep to clearly signaled external materials (OpenAPI, AsyncAPI, Context7, product docs) and in-repo example/test files; no nested reference chains and no bundle files to misorganize.

3 / 3

Total

12

/

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 highly specific, well-triggered description that answers both what and when, names concrete API methods, and cleanly distinguishes itself from the sibling voice-agent skill. No vague fluff or over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions with specific API surface: one-shot REST (`client.speak.v1.audio.generate`), streaming WebSocket (`client.speak.v1.connect`), and the in-repo `deepgram.helpers.TextBuilder` for incremental text assembly.

3 / 3

Completeness

Clearly states what it does (REST + WSS synthesis plus TextBuilder) and opens with an explicit 'Use when writing or reviewing Python code in this repo that calls Deepgram Text-to-Speech v1' trigger clause.

3 / 3

Trigger Term Quality

Explicit trigger list covers natural user terms — "TTS", "speak", "synthesize voice", "aura", "text to speech", "speak.v1", "TextBuilder" — matching what a user would actually say.

3 / 3

Distinctiveness Conflict Risk

Scoped to TTS-only in a specific Python SDK and explicitly redirects full-duplex use to `deepgram-python-voice-agent`, giving it a clear niche unlikely to trigger for 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-python-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.