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".

76

Quality

95%

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

90%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 high-quality, actionable API skill body with copy-paste code for every mode and a strong Gotchas section that surfaces real pitfalls. It is lean and well-structured; the only gap is the absence of an explicit validation/feedback loop, which is less critical for this non-destructive API-usage skill.

DimensionReasoningScore

Conciseness

Lean and assumes Claude's competence: no padding about what TTS is or how libraries work, and every section (auth, REST, WSS, TextBuilder, async, gotchas) earns its tokens; the only mild repetition is the auth note echoed in Gotchas, which is a deliberate consolidation.

5 / 5

Actionability

Fully executable, copy-paste-ready code for REST one-shot, streaming WSS, async equivalents, and the TextBuilder fluent API, covering the common cases with concrete model/encoding values.

5 / 5

Workflow Clarity

Clear sequenced structure (authenticate → REST → WSS → TextBuilder → async → gotchas) with the Gotchas acting as checkpoints for fragile operations, but there is no explicit validate→fix→retry feedback loop.

4 / 5

Progressive Disclosure

Well-organized sections with one-level-deep, clearly signaled references to `reference.md`, example files, and layered external API references (OpenAPI/AsyncAPI/Context7/docs); no bundle directory exists, so structure is judged on the body, which is strong with minor organization gaps.

4 / 5

Total

18

/

20

Passed

Description

100%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 excellent description: it is specific, complete, well-triggered, and explicitly distinguishes itself from a neighboring skill to avoid conflict. Written in the recommended third-person imperative 'Use when...' voice with no first/second-person drift.

DimensionReasoningScore

Specificity

Names the domain and multiple concrete capabilities — one-shot REST (`client.speak.v1.audio.generate`), streaming WebSocket (`client.speak.v1.connect`), and the in-repo `deepgram.helpers.TextBuilder` — giving comprehensive, specific coverage.

5 / 5

Completeness

Explicitly answers both 'what' (writing/reviewing Python calling Deepgram TTS v1, REST + WSS + TextBuilder) and 'when' ("Use when writing or reviewing Python code in this repo that calls Deepgram Text-to-Speech v1") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Lists comprehensive natural triggers a user would actually say — "TTS", "speak", "synthesize voice", "aura", "text to speech", "speak.v1", "TextBuilder" — covering synonyms and SDK-specific phrasings.

5 / 5

Distinctiveness Conflict Risk

Clear TTS-only niche with minimal conflict risk, and it explicitly disambiguates from the sibling skill ("Use `deepgram-python-voice-agent` when you need full-duplex STT + LLM + TTS with barge-in").

5 / 5

Total

20

/

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.

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.