Agent skill

Venice Audio Transcription

Transcribe audio files to text via POST /audio/transcriptions.

Install Venice Audio Transcription

skills CLI

$ npx skills add veniceai/skills --skill venice-audio-transcription -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install veniceai/skills venice-audio-transcription --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/veniceai/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/venice-audio-transcription .claude/skills/venice-audio-transcription && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "venice-audio-transcription" agent skill from https://github.com/veniceai/skills/tree/main/skills/venice-audio-transcription into .claude/skills/venice-audio-transcription/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "venice-audio-transcription", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/veniceai/skills/tree/main/skills/venice-audio-transcription

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add veniceai/skills --skill venice-audio-transcription -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install veniceai/skills venice-audio-transcription --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/veniceai/skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/venice-audio-transcription .agents/skills/venice-audio-transcription && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "venice-audio-transcription" agent skill from https://github.com/veniceai/skills/tree/main/skills/venice-audio-transcription into .agents/skills/venice-audio-transcription/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "venice-audio-transcription", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add veniceai/skills --skill venice-audio-transcription -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install veniceai/skills venice-audio-transcription --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/veniceai/skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/venice-audio-transcription .cursor/skills/venice-audio-transcription && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "venice-audio-transcription" agent skill from https://github.com/veniceai/skills/tree/main/skills/venice-audio-transcription into .cursor/skills/venice-audio-transcription/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "venice-audio-transcription", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/veniceai/skills.git --path skills/venice-audio-transcription

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add veniceai/skills --skill venice-audio-transcription -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install veniceai/skills venice-audio-transcription --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/veniceai/skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/venice-audio-transcription .gemini/skills/venice-audio-transcription && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "venice-audio-transcription" agent skill from https://github.com/veniceai/skills/tree/main/skills/venice-audio-transcription into .gemini/skills/venice-audio-transcription/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "venice-audio-transcription", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install veniceai/skills venice-audio-transcription

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add veniceai/skills --skill venice-audio-transcription -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/veniceai/skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/venice-audio-transcription .github/skills/venice-audio-transcription && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "venice-audio-transcription" agent skill from https://github.com/veniceai/skills/tree/main/skills/venice-audio-transcription into .github/skills/venice-audio-transcription/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "venice-audio-transcription", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add veniceai/skills --skill venice-audio-transcription -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install veniceai/skills venice-audio-transcription --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/veniceai/skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/venice-audio-transcription .opencode/skills/venice-audio-transcription && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "venice-audio-transcription" agent skill from https://github.com/veniceai/skills/tree/main/skills/venice-audio-transcription into .opencode/skills/venice-audio-transcription/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "venice-audio-transcription", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: venice-audio-transcription
GitHub stars: 144
Token cost: ~1.7k tokens
SKILL.md length: 630 words
Files: 1
Skills in repo: 22
Repo updated: Oct 5, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Transcribe audio files to text via POST /audio/transcriptions.

Tasks that involve Transcription
SKILL.md covers Use when, Minimal request, Request (multipart/form-data) and Response, plus 5 more sections
Calls curl and ffmpeg; reaches api.venice.ai; needs VENICE_API_KEY

What it does

Venice Audio Transcription is an agent skill from veniceai/skills. Transcribe audio files to text via POST /audio/transcriptions. Covers supported models (Parakeet, Whisper, Wizper, Scribe, xAI STT), accepted containers (wav/flac/m4a/aac/mp4/mp3/ogg/webm), response formats (json/text only), per-model timestamps (word/segment/char), language hints, the 25 MB cap, and per-audio-second pricing. OpenAI-compatible multipart.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Media & Creative, covering Transcription. It works with OpenAI. The repository describes itself as: Agent Skills for the Venice.ai API. One folder per surface area, each with a SKILL.md for agent runtimes (Cursor, Claude, Codex, etc.). The licence is MIT.

When your agent uses it

Tasks that involve Transcription

Example prompts

“/venice-audio-transcription”

Requirements

A credential in VENICE_API_KEY

What it can do on your machine

Read from SKILL.md and the folder at commit 5eaeac5. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- curl
- ffmpeg
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
- api.venice.ai
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
- VENICE_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Venice Audio Transcription loads about 1.7k tokens when it runs. Until then it costs about 96 tokens; SKILL.md has 630 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~96
When it runs · the whole SKILL.md, loaded when a task matches: ~1.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from veniceai/skills at commit 5eaeac5, republished under its MIT licence (© veniceai). 630 words, ~1,735 tokens.

Download SKILL.mdSave it as .claude/skills/venice-audio-transcription/SKILL.md (or your agent's skills folder).

name: venice-audio-transcription
description: Transcribe audio files to text via POST /audio/transcriptions. Covers supported models (Parakeet, Whisper, Wizper, Scribe, xAI STT), accepted containers (wav/flac/m4a/aac/mp4/mp3/ogg/webm), response formats (json/text only), per-model timestamps (word/segment/char), language hints, the 25 MB cap, and per-audio-second pricing. OpenAI-compatible multipart.

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.

Method	Path	Auth	Notes
`POST`	`/api/v1/audio/transcriptions`	Bearer key or x402 (SIWX)	`multipart/form-data`, file field `file`, max 25 MB. Billed per second of audio.

Use when

You need STT (speech-to-text) for voice notes, meetings, podcasts, short audio.
You need word/segment timestamps for subtitles or chapters.
You want to pick between Venice-hosted Parakeet, Whisper-family models, ElevenLabs Scribe, or xAI STT.

For video, there is no transcription endpoint any more — POST /video/transcriptions is retired and returns 410. Extract the audio track and send it here, or ask a video-capable chat model via venice-chat.

Minimal request

bash

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"

json

{ "text": "Alright everyone, let's kick off the meeting...", "duration": 184.2 }

With timestamps=true, the JSON also carries a timestamps object (see below).

Request (`multipart/form-data`)

Only the fields below are read; anything else in the form is ignored.

Field	Type	Default	Notes
`file`	binary	—	Required. Real file part (no base64). Accepted: `wav`/`wave`, `flac`, `m4a`, `aac`, `mp4`, `mp3`, `ogg`/`oga`, `webm`. Checked by extension/MIME and then by binary signature. Max 25 MB.
`model`	string	—	Send it. The OpenAPI schema lists `nvidia/parakeet-tdt-0.6b-v3` as default, but that default is never applied: omitting `model` returns `400 "model is required"`.
`response_format`	`json` / `text`	`json`	Only these two. `text` returns a `text/plain` body with just the transcript.
`timestamps`	bool (`true`/`false` as form string)	`false`	Adds `timestamps` to the JSON response.
`language`	string	—	ISO 639-1 hint (`en`, `ja`, …). Forwarded by Whisper, Wizper, Scribe and xAI STT; ignored by Parakeet (auto-detects).

Response

json

{
  "text": "…",
  "duration": 184.2,
  "timestamps": {
    "word":    [{ "word": "Alright", "start": 0.12, "end": 0.48 }],
    "segment": [{ "text": "Alright everyone…", "start": 0.12, "end": 4.9 }],
    "char":    [{ "char": "A", "start": 0.12, "end": 0.15 }]
  }
}

duration (seconds) and timestamps are optional. Which timestamp arrays appear depends on the model:

Model	Timestamp granularity
`openai/whisper-large-v3`	`segment` + `word`
`fal-ai/wizper`	`segment`
`elevenlabs/scribe-v2`	`word`
`stt-xai-v1`	`word`
`nvidia/parakeet-tdt-0.6b-v3`	may include `segment`, `word` and/or `char`

Models

All five are in the live GET /models?type=asr list. Price is model_spec.pricing.per_audio_second.usd.

Model ID	Privacy	Notes
`nvidia/parakeet-tdt-0.6b-v3`	private	Venice-hosted, fast. Ignores `language`.
`openai/whisper-large-v3`	private	Multilingual; `language` hint; segment + word timestamps.
`fal-ai/wizper`	private	Whisper v3 variant; `language` hint; segment timestamps.
`elevenlabs/scribe-v2`	anonymized	`language` hint; word timestamps.
`stt-xai-v1`	anonymized	`language` hint; word timestamps.

A key with modelPrivacy: PRIVATE_ONLY gets 403 on the anonymized ones (PRIVATE_TEXT keys are not restricted here). Failed transcriptions are not charged.

OpenAI SDK

import OpenAI from 'openai'
import fs from 'node:fs'

const client = new OpenAI({
  apiKey: process.env.VENICE_API_KEY,
  baseURL: 'https://api.venice.ai/api/v1',
})

const out = await client.audio.transcriptions.create({
  file: fs.createReadStream('meeting.m4a'),
  model: 'openai/whisper-large-v3',
  response_format: 'json',
  language: 'en',
  // @ts-expect-error — Venice-specific extra, passes through multipart
  timestamps: true,
})

console.log(out.text)

Long files

There's no server-side chunking, and uploads are capped at 25 MB. Split long recordings client-side (on silence, or fixed segments), transcribe each chunk, then concatenate with offset timestamps.

bash

ffmpeg -i long.mp3 -f segment -segment_time 600 -c copy chunk_%03d.mp3

Show full SKILL.md (246 more words)Show less

Errors

Code	Meaning
`400`	Missing `model`, bad params (e.g. `response_format` not `json`/`text`), no `file` part (including a JSON body instead of multipart → `"No audio file provided"`), unsupported extension/MIME, or unrecognized binary signature.
`401`	Authentication failed.
`402`	Insufficient balance. Bearer → `{"error":"Insufficient USD or Diem balance…"}`, or `"API key USD
`403`	A `PRIVATE_ONLY` key calling an `anonymized` model, or region restriction.
`404`	Unknown `model`.
`413`	File larger than 25 MB (`{"code":"PAYLOAD_TOO_LARGE","error":"File exceeds the maximum allowed size of 25 MB."}`).
`422`	Upstream provider couldn't process the audio (zero-length, silent, corrupt, unsupported format or language, provider-side refusal). No `suggested_prompt`.
`429`	Rate limited.
`500`	Inference failure.
`502`	Temporary upstream ASR failure — `{"error":"Audio transcription failed due to a temporary upstream error. Please retry."}` (no `code` field). Retry with backoff.
`503`	Model temporarily offline — retry with jitter.

See venice-errors for body shapes and retry strategy.

Gotchas

Always send model — the documented default never applies.
file must be a real multipart file part. JSON + base64 is not supported.
There is no verbose_json, srt or vtt. For subtitles, use response_format=json + timestamps=true and render the timings yourself. text drops timestamps entirely.
Check which granularity your model returns before building on timestamps.word vs timestamps.segment.
A file with a valid extension but a non-audio binary signature is rejected; re-encode to a standard profile (e.g. MP3 44.1 kHz or 16 kHz).
On 429, back off; throttle big batches rather than firing everything in parallel.

Files

Just SKILL.md in skills/venice-audio-transcription of veniceai/skills.

Open the folder on GitHubat commit 5eaeac5

Compare with similar skills

Venice Audio Transcription next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Venice Audio Transcription compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Venice Audio Transcription this skillveniceai/skills	144	—	~1.7k	Automated safety check: Pass	MIT	5 days ago
9Router Speech-to-Textdecolua/9router	31k	—	~914	Automated safety check: Pass	MIT	2 days ago
TranscribeJetBrains/skills	366	4 repos	~776	Automated safety check: Pass	Apache-2.0	3 mo ago
Openai Whisper APIopenclaw/openclaw	392k	1 repos	~518	Automated safety check: Pass	MIT	today
Local AI Useamd/skills	408	—	~5k	Automated safety check: Notes	MIT	yesterday
Local AI App Integrationamd/skills	408	—	~6k	Automated safety check: Pass	MIT	yesterday

Similar skills

9Router Speech-to-Text
decolua/9router
Transcribes audio files into text or subtitles through 9Router's Whisper-compatible endpoint, using models from OpenAI, Groq, Gemini, Deepgram and others.
31k GitHub stars~914 tokensUpdated 2 days ago
Media & CreativeAuto-check passed
Transcribe
JetBrains/skills
Official
Transcribe audio files to text with optional diarization and known-speaker hints.
366 GitHub starsUsed in 4 repos~776 tokens
Media & CreativeAuto-check passed
Openai Whisper API
openclaw/openclaw
OpenAI Audio Transcriptions API via curl; gpt-4o-transcribe, mini, diarize, or whisper-1.
392k GitHub starsUsed in 1 repo~518 tokens
Media & CreativeAuto-check passed
Local AI Use
amd/skills
Makes this agent generate images, transcribe audio, and synthesize speech on the user's own machine through a local Lemonade Server instead of a paid cloud API.
408 GitHub stars~5k tokensUpdated yesterday
Media & CreativeAuto-check: notes
Local AI App Integration
amd/skills
Integrates local AI capabilities into applications using Embeddable Lemonade.
408 GitHub stars~6k tokensUpdated yesterday
Media & CreativeAuto-check passed
Azure AI
microsoft/GitHub-Copilot-for-Azure
Official
A skill your agent uses for Azure AI: Search, Speech, OpenAI, Document Intelligence.
255 GitHub starsUsed in 1 repo~852 tokens
Media & CreativeAuto-check passed

Questions about Venice Audio Transcription

What does Venice Audio Transcription do?

Transcribe audio files to text via POST /audio/transcriptions. Venice Audio Transcription is an agent skill from veniceai/skills. Transcribe audio files to text via POST /audio/transcriptions.

When should I use Venice Audio Transcription?

Venice Audio Transcription fits situations like: tasks that involve Transcription.

How do I install Venice Audio Transcription in Claude Code?

Run `npx skills add veniceai/skills --skill venice-audio-transcription -a claude-code`. Or copy the skill folder (skills/venice-audio-transcription in veniceai/skills) into .claude/skills/venice-audio-transcription in your project. Claude Code loads it when a task matches its description.

How do I install Venice Audio Transcription in Codex?

Run `npx skills add veniceai/skills --skill venice-audio-transcription -a codex`. Or copy the skill folder (skills/venice-audio-transcription in veniceai/skills) into .agents/skills/venice-audio-transcription in your project. Codex loads it when a task matches its description.

Can I use Venice Audio Transcription in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add veniceai/skills --skill venice-audio-transcription -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/venice-audio-transcription, .gemini/skills/venice-audio-transcription, .github/skills/venice-audio-transcription and .opencode/skills/venice-audio-transcription in your project.

What does Venice Audio Transcription need to run?

Going by SKILL.md and its folder, Venice Audio Transcription needs the command-line tools its instructions call (curl and ffmpeg) and credentials named VENICE_API_KEY. Our summary lists: A credential in VENICE_API_KEY.

Does Venice Audio Transcription access the network?

SKILL.md names 1 domain. In commands or code: api.venice.ai; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Venice Audio Transcription safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Venice Audio Transcription use?

Venice Audio Transcription is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Venice Audio Transcription use?

About 1.7k tokens (SKILL.md is roughly 6.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Venice Audio Transcription?

Skills that share tags, products or a category with Venice Audio Transcription: 9Router Speech-to-Text (decolua/9router, 31k stars), Transcribe (JetBrains/skills, 366 stars), Openai Whisper API (openclaw/openclaw, 392k stars) and Local AI Use (amd/skills, 408 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Venice Audio Transcription?

veniceai (a GitHub organization) maintains it in veniceai/skills, which has 144 GitHub stars. The repository holds 22 skills in this directory. The repository was last updated on October 5, 2026.

Source: veniceai/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Venice Audio Transcription

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Venice Transcription (/audio/transcriptions)

Use when

Minimal request

Request (multipart/form-data)

Response

Models

OpenAI SDK

Long files

Errors

Gotchas

Files

Compare with similar skills

Similar skills

More from veniceai/skills

Related

Questions about Venice Audio Transcription

Venice Transcription (`/audio/transcriptions`)

Request (`multipart/form-data`)