Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add 0xatd/cheaptokens-skills --skill venice-audio-transcriptiongit clone --depth 1 https://github.com/0xatd/cheaptokens-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/0xatd/cheaptokens-skills/venice-audio-transcription)<a href="https://agentmods.dev/skills/0xatd/cheaptokens-skills/venice-audio-transcription"><img src="https://agentmods.dev/badge/skills/0xatd/cheaptokens-skills/venice-audio-transcription/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/0xatd/cheaptokens-skills/venice-audio-transcription"><img src="https://agentmods.dev/badge/skills/0xatd/cheaptokens-skills/venice-audio-transcription.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00078 | $0.01301 |
| Opus 5 | $0.00039 | $0.00651 |
| Sonnet 5 | $0.00016 | $0.00260 |
| Haiku 4.5 | $0.00008 | $0.00130 |
Grade A, and why
venice-audio-transcription scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl https://api.venice.ai/api/v1/audio/transcriptions \ This is a copy
100% identical to venice-audio-transcription — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Venice Transcription (/audio/transcriptions)
POST /api/v1/audio/transcriptions takes an audio file and returns text. It's OpenAI-compatible with multipart/form-data — the OpenAI SDK's audio.transcriptions.create() works unchanged.
Use when
- You need STT (speech-to-text) for voice notes, meetings, podcasts, short audio.
- You need timestamps for subtitles / chapters.
- You want to pick between fast local-style models (Parakeet) and large multilingual ones (Whisper, Wizper, Scribe).
For long video / YouTube transcription, see venice-video's /video/transcriptions (takes a public video URL directly).
Minimal request
curl https://api.venice.ai/api/v1/audio/transcriptions \
-H "Authorization: Bearer $VENICE_API_KEY" \
-F "file=@./meeting.m4a" \
-F "model=nvidia/parakeet-tdt-0.6b-v3" \
-F "response_format=json" \
-F "timestamps=false"
{ "text": "Alright everyone, let's kick off the meeting..." }
With timestamps=true, json format also returns segment/word timings (schema is model-specific).
Request (multipart/form-data)
| Field | Type | Default | Notes |
|---|---|---|---|
file |
binary | — | Required. Audio file. Supported: wav, wave, flac, m4a, aac, mp4, mp3, ogg, webm. Base64 is not accepted — upload as a real file. |
model |
enum | nvidia/parakeet-tdt-0.6b-v3 |
See models below. |
response_format |
json / text |
json |
text returns text/plain body. |
timestamps |
bool | false |
Include segment/word timestamps (JSON only). |
language |
string | — | ISO 639-1 hint (e.g. en, ja). Only Whisper-family models honor it; others auto-detect. |
Models
| Model ID | Notes |
|---|---|
nvidia/parakeet-tdt-0.6b-v3 |
Default. Fast, English-first, great for real-time-ish flows. |
openai/whisper-large-v3 |
Large multilingual, honors language hint. |
fal-ai/wizper |
Whisper variant, competitive on quality/latency tradeoff. |
elevenlabs/scribe-v2 |
ElevenLabs Scribe, strong on noisy audio. |
stt-xai-v1 |
xAI Speech-to-Text. |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 107 lines · 78 tokens per session scan A 0b0b4e80796e
venice-audio-transcription is a skill published in the GitHub repository 0xatd/cheaptokens-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 78 tokens to every session and 1,301 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 100% identical to venice-audio-transcription, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
bridgenode
BridgeNode MCP wrapper — stdio MCP server proxying to remote streamable-HTTP endpoint with automatic x402 payment on Solana USDC. No API keys. Use when an agent needs LLM inference through MCP (Claude Code, Cursor, etc.) and has no provider API key.
groq-inference
Ultra-fast LLM inference on custom LPU hardware. OpenAI-compatible API at api.groq.com. Lowest latency in the industry (500-1000+ tok/s). Supports chat completions, vision, audio (Whisper STT + TTS), tool calling, JSON mode, and streaming. Free tier available. Inference only — no training.
image-prompting
Use when generating or editing images via blockrunimage — especially with GPT Image 2, Nano Banana, or Grok Imagine for posters, UI mockups, marketing assets, product shots, or anything with on-image text. Turns vague user requests ("make me a cool poster") into structured, text-accurate prompts that actually render…
gentech-blockrun
GenTech Labs' integration patterns for BlockRun MCP from Hermes Agent. Covers daily usage patterns, cost-optimized workflows, multi-tool pipelines, and reliable error handling for BlockRun's full toolset.
surf
Surf (asksurf.ai) is RETIRED on BlockRun and the blockrunsurf tool was REMOVED in 0.49.0 — the gateway has answered every /v1/surf/ path with HTTP 410 endpointretired since 2026-09-06. Use this skill to route a former Surf question (on-chain SQL, wallet labels and net worth, CEX order books, social mindshare, news) to…
search
Use when the user wants real-time web or news results with AI-summarized answers and citations — Grok Live Search via BlockRun. Cheapest path for "what just happened" questions where freshness beats neural-semantic ranking.