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".

68

Quality

82%

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

64%

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

This is a solid, highly actionable skill with excellent executable code examples covering REST, WebSocket, async, and callback patterns. Its main weaknesses are moderate verbosity (some sections could be tightened or split into separate files) and the absence of explicit validation/error-handling checkpoints in workflows. The routing guidance to other skills and the gotchas section add genuine value.

Suggestions

Add error handling and validation checkpoints to workflows — e.g., check response status, handle connection failures in WebSocket, and show a try/except pattern for common errors like auth failures or encoding mismatches.

Consider moving the 'Interim vs. final flag semantics' and 'Async / deferred result patterns' sections to separate reference files, keeping only a brief summary and link in the main SKILL.md to reduce its length.

DimensionReasoningScore

Conciseness

The skill is generally well-structured but includes some unnecessary verbosity. The 'Interim vs. final flag semantics' section and the 'Async / deferred result patterns' section with its comparison table are thorough but could be tightened. The 'When to use this product' and 'Use a different skill when' sections are useful routing info but add length. The WebSocket example includes extensive inline comments that border on over-explanation. Some sections like 'Key parameters' are just a list of names without descriptions, which is either too terse to be useful or should be omitted entirely.

2 / 3

Actionability

The skill provides fully executable, copy-paste-ready code examples for all major use cases: REST URL transcription, REST file transcription, WebSocket streaming with interim results, async equivalents, and callback patterns. Import paths are specific, method signatures are complete, and the response traversal path (response.results.channels[0].alternatives[0].transcript) is explicit.

3 / 3

Workflow Clarity

The skill covers multiple workflows (REST, WebSocket, async, callback) with clear sequencing within each. However, there are no explicit validation checkpoints — for example, no error handling patterns, no guidance on checking response status codes, no verification that transcription succeeded before using results. The WebSocket workflow is well-sequenced (connect → register handlers → start listening → send audio → finalize) but lacks error recovery steps.

2 / 3

Progressive Disclosure

The skill references external files (reference.md, example files, external URLs) and other skills appropriately, but the main body is quite long (~200+ lines) with substantial inline content that could be split out. The interim/final semantics section, the async/deferred patterns comparison, and the gotchas could each be separate reference files. The API reference section with its layered approach is well-structured for progressive disclosure, but the overall document is monolithic.

2 / 3

Total

9

/

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 distinguishes itself from related skills. The inclusion of specific API methods, endpoint paths, and boundary guidance with sibling skills makes it highly effective for skill selection among 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 explicitly names the endpoint '/v1/listen'.

3 / 3

Completeness

Clearly answers both 'what' (Python code calling Deepgram STT v1 for prerecorded/live transcription via REST and WebSocket) and 'when' (explicit 'Use when' clause at the start, plus explicit trigger terms and boundary conditions distinguishing from 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 delineates boundaries with four related skills (audio-intelligence, conversational-stt, voice-agent), specifying exactly which features belong to each. This makes conflict with sibling skills very unlikely.

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.