CtrlK
BlogDocsLog inGet started
Tessl Logo

deepgram-python-speech-to-text

Use when writing or reviewing Python code in this repo that calls Deepgram Speech-to-Text v1 (`/v1/listen`) for prerecorded or live audio transcription. Covers `client.listen.v1.media.transcribe_url` / `transcribe_file` (REST) and `client.listen.v1.connect` (WebSocket). Use this skill for basic ASR; use `deepgram-python-audio-intelligence` for summarize/sentiment/topics/diarize overlays, `deepgram-python-conversational-stt` for turn-taking v2/Flux, and `deepgram-python-voice-agent` for full-duplex assistants. Triggers include "transcribe", "live transcription", "speech to text", "STT", "listen endpoint", "nova-3", "listen.v1".

72

Quality

88%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

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.

This is a strong, highly actionable skill with excellent executable code examples covering all major use cases (REST, WebSocket, async, callback). The workflow clarity is good with explicit sequencing and validation steps. The main weakness is length — the skill packs a lot of inline content that could benefit from being split into referenced files for better progressive disclosure, and some sections (interim flag semantics, async patterns comparison) are more verbose than necessary for a skill document.

Suggestions

Consider moving the detailed 'Interim vs. final flag semantics' and 'Async / deferred result patterns' sections into separate referenced files to reduce the main skill's token footprint.

Trim inline comments in code examples that explain things Claude already knows (e.g., '# Mutable container so the on_message closure can update state without `global`').

DimensionReasoningScore

Conciseness

The skill is generally well-structured but includes some unnecessary verbosity — the interim vs. final flag semantics section is quite detailed, the async/deferred patterns section is lengthy with a comparison table, and some inline comments over-explain. The 'when to use this product' and 'use a different skill' sections are useful but could be tighter. Overall mostly efficient but not maximally lean.

2 / 3

Actionability

Every major use case (REST URL, REST file, WebSocket streaming, async, callback) has fully executable, copy-paste-ready Python code with correct imports and realistic parameters. The gotchas section provides specific, concrete guidance on common failure modes with exact details (e.g., 'bytes not file handle', 'Token not Bearer').

3 / 3

Workflow Clarity

The WebSocket workflow clearly sequences connection setup → event handlers → background listener thread → send audio → send_finalize → close. The interim/final flag semantics provide explicit decision logic. The callback pattern clearly explains the async flow (returns immediately, webhook receives result, no polling). Clean stream closure is explicitly called out as a validation step in gotchas.

3 / 3

Progressive Disclosure

The skill references example files and external docs (reference.md, OpenAPI/AsyncAPI specs, Context7), which is good. However, the body itself is quite long (~200+ lines) with substantial inline content (the full async/deferred patterns section, the detailed interim flag semantics) that could be split into separate reference files. The API reference section nicely layers sources, but no bundle files exist to verify referenced paths.

2 / 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.

This is an excellent skill description that clearly defines its scope (Deepgram STT v1 for prerecorded/live transcription), provides explicit trigger terms, and carefully delineates boundaries with related skills. It is specific, complete, and highly distinctive, making it easy for Claude to select the right skill from a large pool.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions and API methods: 'transcribe_url', 'transcribe_file' (REST), 'client.listen.v1.connect' (WebSocket), prerecorded and live audio transcription. Also names the exact endpoint '/v1/listen'.

3 / 3

Completeness

Clearly answers both 'what' (calls Deepgram STT v1 for prerecorded/live audio transcription via REST and WebSocket) and 'when' (explicit 'Use when writing or reviewing Python code... that calls Deepgram Speech-to-Text v1'). Also explicitly delineates boundaries with related skills.

3 / 3

Trigger Term Quality

Excellent coverage of natural trigger terms users would say: 'transcribe', 'live transcription', 'speech to text', 'STT', 'listen endpoint', 'nova-3', 'listen.v1'. These cover both casual and technical variations.

3 / 3

Distinctiveness Conflict Risk

Exceptionally distinctive — explicitly names sibling skills and draws clear boundaries ('use deepgram-python-audio-intelligence for summarize/sentiment/topics/diarize overlays', etc.), making it very unlikely to conflict with related skills.

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.

Validation11 / 11 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.