zai-asr-skill

zai-asr-skill is a skill for OpenCode from darellchua2/opencode-config-template. It costs 59 tokens per session (907 once invoked), scanned A, original, Apache-2.0.

An audio-transcription recipe that sends WAV or MP3 files to Z.AI’s GLM-ASR service and returns the spoken words as text. ASR means automatic speech recognition.

In plain words
What is it for?
Use it for transcribing short audio recordings, or for converting longer recordings into ordered text segments.
Why use it?
It removes the need to type recordings manually, while longer files can be split into shorter parts first.

Skill for OpenCode

Written for OpenCode: installed under .opencode/. Also seen: positional $N argument; mentions OpenCode.

Good fit Use it for transcribing short audio recordings, or for converting longer recordings into ordered text segments.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/darellchua2/opencode-config-template/zai-asr-skill
Install

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.

Any agent
npx skills add darellchua2/opencode-config-template --skill zai-asr-skill
Clone the repo
git clone --depth 1 https://github.com/darellchua2/opencode-config-template

Made for: OpenCode.

Wrote 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.

agentmods badge for zai-asr-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/darellchua2/opencode-config-template/zai-asr-skill.svg)](https://agentmods.dev/skills/darellchua2/opencode-config-template/zai-asr-skill)
Your own site
<a href="https://agentmods.dev/skills/darellchua2/opencode-config-template/zai-asr-skill"><img src="https://agentmods.dev/badge/skills/darellchua2/opencode-config-template/zai-asr-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 907 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00059 $0.00907
Opus 5 $0.00030 $0.00453
Sonnet 5 $0.00012 $0.00181
Haiku 4.5 $0.00006 $0.00091

Measured 4d ago against content hash c04b85a0cb7b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

zai-asr-skill 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 4d 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.

RESP=$(curl -sS --max-time 120 -X POST "$BASE/audio/transcriptions" \
opencode_app/.opencode/skills/zai-asr-skill/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

What I do

I provide the exact recipe for an agent to transcribe an audio file via the Z.AI GLM-ASR API and return the transcript text. OpenCode has no voice-input path, so transcription happens as a file-based tool call: POST /audio/transcriptions.

Constraints (hard limits — check before calling)

  • Models: glm-asr-2512
  • File: ≤ 25 MB, ≤ 30 seconds, .wav or .mp3
  • Longer audio must be split first (e.g. ffmpeg -f segment -segment_times <n>) — transcribe the segments in order and concatenate.

Prerequisite — API key resolution

KEY="${ZAI_API_KEY:-$(jq -r '.["zai"].key // .["zai-coding-plan"].key // empty' \
     ~/.local/share/opencode/auth.json 2>/dev/null)}"
[ -z "$KEY" ] && { echo "ZAI_API_KEY not found — set it (export ZAI_API_KEY) or run \`opencode auth login\` (Z.AI)."; exit 1; }

If neither source has the key, stop and report — do not proceed.

Recipe

# --- options ---
FILE="path/to/audio.mp3"                              # REQUIRED — .wav or .mp3, ≤25MB, ≤30s
BASE="${ZAI_MEDIA_ENDPOINT:-https://api.z.ai/api/paas/v4}"  # pay-as-you-go ONLY

# pre-flight: size + duration guards
[ -f "$FILE" ] || { echo "No such file: $FILE"; exit 1; }
[ "$(wc -c <"$FILE")" -le 26214400 ] || { echo "File >25MB — split it first"; exit 1; }

RESP=$(curl -sS --max-time 120 -X POST "$BASE/audio/transcriptions" \
  -H "Authorization: Bearer $KEY" \
  -F "model=glm-asr-2512" \
  -F "file=@$FILE")

TEXT=$(printf '%s' "$RESP" | python3 -c '
import sys, json
d = json.load(sys.stdin)
if d.get("error"):
    sys.stderr.write("API error: " + json.dumps(d["error"]) + "\n"); sys.exit(1)
print(d.get("text",""))') || { echo "Transcription failed. Response: $RESP"; exit 1; }
echo "TRANSCRIPT: $TEXT"

Output: the transcript on the TRANSCRIPT: line.

Error handling

Condition Detect Action
Missing key [ -z "$KEY" ] Stop; tell caller to set ZAI_API_KEY
File too large / long pre-flight check Split with ffmpeg; transcribe segments; concatenate
Wrong format file extension not wav/mp3 Convert: ffmpeg -i in -ar 16000 out.wav
API error (auth/quota/format) response JSON has "error" Print error body; report Status: failed
Empty transcript text empty File may be silent — report, don't retry
Rate limited HTTP 429 Wait and retry once; otherwise report

Read the full file on GitHub · 83 lines

Changes

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.

  1. 4d ago First seen · 83 lines · 59 tokens per session scan A c04b85a0cb7b

Subscribe to this mod's changes

zai-asr-skill is a skill published in the GitHub repository darellchua2/opencode-config-template (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 59 tokens to every session and 907 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

minimax-cli

Nested swiss-knife reference for the MiniMax mmx CLI and the canonical MiniMax CLI procedure shipped with the TUI: install mmx-cli, discover the correct TUI-managed MiniMax preset/key slot without leaking secrets, match mainland vs international regions, and route image/video/music/TTS generation or one-shot shell…

Lingtai-AI/lingtai · 72 tokens

media-generation

Generate and edit images, create videos, synthesize speech, transcribe and translate audio using multiple AI providers (OpenAI, Google, ElevenLabs, Deepgram, Fal, Luma, Replicate, Stability, Runway, OpenRouter, Edge TTS). Use when the user asks to create media assets, generate pictures, make videos, produce…

onimusya/media-gen · 88 tokens

kling-video

Generate AI videos using Kling video generation models. Use when you need to: (1) create videos from text prompts, (2) animate images into videos, (3) transform existing videos with AI, or (4) create AI avatar videos with speech.

refly-ai/refly-skills · 56 tokens

webgl-holographic-foil

A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.

nexu-io/open-design · 41 tokens

general-video

Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…

heygen-com/hyperframes · 92 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens