Agent skill · marketing growth · jeremylongshore
deepgram-cost-tuning
Optimize Deepgram costs and usage for budget-conscious deployments.
Why this skill is useful
Provides domain-specific knowledge on optimizing Deepgram API costs and includes a budget-aware transcription service implementation.
What it needs
Requires deepgram account access. About 6k tokens when loaded. Last updated 2026-08-07. 2,604 stars on the source repository.
What this skill does
Deepgram Cost Tuning Prerequisites An aggregate usage/cost baseline, approved budget owner, delivery/quality SLO, and data/retention policy. Synthetic fixtures and a reversible optimization/change record. Examples Compare aggregate duration, model, concurrency, and error data in a development/staging workload, change one approved model or batching parameter, and observe the quality/latency/cost tradeoff. Revert if quality or reliability drops; do not reduce retention, privacy, or consent safeguards merely to lower spend. Overview Optimize Deepgram API costs through smart model selection, audio preprocessing to reduce billable minutes, usage monitoring via the Deepgram API, budget guardrails, and feature-aware cost estimation. Deepgram bills per audio minute processed. Deepgram Pricing (2026) Product Model Price/Minute Notes --------- ------- ------------- ------- STT (Batch) Nova-3 $0.0043 Best accuracy STT (Batch) Nova-2 $0.0043 Proven stable STT (Streaming) Nova-3 $0.0059 Real-time STT (Streaming) Nova-2 $0.0059 Real-time STT (Batch) Base $0.0048 Fastest STT (Batch) Whisper $0.0048 Multilingual TTS Aura-2 Pay-per-character See TTS pricing Intelligence Summarize/Topics/Sentiment Included with STT No extra cost Add-on costs: Diarization: +$0.0044/min Multichannel: billed per channel Instructions Step 1: Budget-Aware Transcription Service Step 2: Reduce Billable Minutes with Audio Preprocessing Step 3: Query Deepgram Usage API Step 4: Cost-Optimized Model Selection Step 5: Feature Cost Awareness Output Budget-aware transcription with auto-blocking Audio preprocessing to reduce billable minutes Usage dashboard via Deepgram API Cost-optimized model recommendation Feature cost breakdown with estimation Cost Optimization Quick Wins Strategy Savings Effort ---------- --------- -------- Remove silence from audio 10-40% Low (ffmpeg one-liner) Disable diarization when not needed ~50% Low (remove option) Use callback for long files Indirect (no timeouts) Low Cache repeated tr …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills jeremylongshore/deepgram-cost-tuning--27fe54