New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Venice Audio Voice Changer

by veniceai in veniceai/skills

Async speech-to-speech voice conversion via Venice — re-record a source recording in a different voice while keeping delivery and timing.

MITAuto-check passedMedia & Creative

Install Venice Audio Voice Changer

skills CLI
$ npx skills add veniceai/skills --skill venice-audio-voice-changer -a claude-code

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

GitHub CLI
$ gh skill install veniceai/skills venice-audio-voice-changer --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-voice-changer .claude/skills/venice-audio-voice-changer && 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/

Facts

Skill name
venice-audio-voice-changer
GitHub stars
144
Token cost
~2.8k tokens
SKILL.md length
1,025 words
Files
1
Skills in repo
22
Repo updated
First seen
Licence
MIT

At a glance

Async speech-to-speech voice conversion via Venice — re-record a source recording in a different voice while keeping delivery and timing.

  • Works in 4 steps: POST /audio/voice-changer/quote → POST /audio/voice-changer/queue → POST /audio/voice-changer/retrieve → …
  • Media & Creative work in your project
  • SKILL.md covers Use when, Discover models, Lifecycle and Full loop (TypeScript), plus 2 more sections
  • Calls curl; reaches api.venice.ai; needs VENICE_API_KEY

What it does

Venice Audio Voice Changer is an agent skill from veniceai/skills. Async speech-to-speech voice conversion via Venice — re-record a source recording in a different voice while keeping delivery and timing. Covers POST /audio/voice-changer/quote (unauthenticated), /queue (multipart file or JSON audiourl), /retrieve and /complete, how to discover voice-changer models (modelspec.voicechanger on /models?type=music), accepted formats, the source-length cap, whole-minute billing, refunds, and what each endpoint refuses. Note that no voice-changer model is currently open to regular API…

Its SKILL.md is about 2.8k 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. It works with x402. 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

  • Media & Creative work in your project

Example prompts

  • “/venice-audio-voice-changer”

Requirements

  • A credential in VENICE_API_KEY

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. POST /audio/voice-changer/quote
  2. POST /audio/voice-changer/queue
  3. POST /audio/voice-changer/retrieve
  4. POST /audio/voice-changer/complete

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

    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 Voice Changer loads about 2.8k tokens when it runs. Until then it costs about 138 tokens; SKILL.md has 1,025 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~138
When it runs · the whole SKILL.md, loaded when a task matches
~2.8k

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). 1,025 words, ~2,821 tokens.

Download SKILL.mdSave it as .claude/skills/venice-audio-voice-changer/SKILL.md (or your agent's skills folder).
name
venice-audio-voice-changer
description
Async speech-to-speech voice conversion via Venice — re-record a source recording in a different voice while keeping delivery and timing. Covers POST /audio/voice-changer/quote (unauthenticated), /queue (multipart file or JSON audio_url), /retrieve and /complete, how to discover voice-changer models (model_spec.voice_changer on /models?type=music), accepted formats, the source-length cap, whole-minute billing, refunds, and what each endpoint refuses. Note that no voice-changer model is currently open to regular API keys.

Venice Voice Changer (/audio/voice-changer/*)

Speech-to-speech conversion: upload a recording, get the same speech back in a different voice, with the original pacing, emotion and timing preserved. It's asynchronous, with its own quote → queue → retrieve → complete family (parallel to, but separate from, venice-audio-music).

Availability (checked 2026-09-30): the endpoints are in the public API spec, but the only voice-changer model, elevenlabs-voice-changer, is not yet open to regular API keys. It is not listed by GET /models, and regular keys (or no key) get 404 "Specified model not found" from every endpoint below. Before using this skill, confirm that a model with model_spec.voice_changer: true shows up in GET /models?type=music for your key; if none does, the feature isn't available to you.

MethodPathAuthNotes
POST/api/v1/audio/voice-changer/quoteNone required (key optional)Price for a source of N seconds.
POST/api/v1/audio/voice-changer/queueBearer key or x402 (SIWX)multipart/form-data (file) or JSON (audio_url). Charges and enqueues. 40 req/min per user.
POST/api/v1/audio/voice-changer/retrieveBearer key or x402 (SIWX)Status JSON or the converted audio. 120 req/min per user.
POST/api/v1/audio/voice-changer/completeBearer key or x402 (SIWX)Release the provider-held media.

Each endpoint only accepts voice-changer models (400 otherwise, naming the endpoint to use instead), and /audio/quote, /audio/queue, /audio/retrieve, /audio/complete refuse voice-changer models the same way.

Use when

  • You have a real recording (voice-over, dialogue, a take) and want it in another voice without re-performing it.
  • You want to keep the timing of the original exactly — e.g. dubbing against picture.

For text → speech use venice-audio-speech; to create a reusable voice from a sample, see voice cloning there.

Discover models

There is no ?type=voice-changer filter. Voice-changer models are music-type models whose model_spec carries:

FieldMeaning
voice_changertrue on voice-changer models only.
accepted_audio_formatsContainers accepted for the source, judged from the file's bytes (not its name or Content-Type). mp4 covers M4A.
max_source_audio_duration_secondsLongest source accepted; longer → 422 before any charge.
supports_background_noise_removalWhether remove_background_noise is honored.
supports_seedWhether seed is honored.
voices, default_voice, supports_custom_voice_idTarget voices; with supports_custom_voice_id: true you may pass a provider Voice ID.
pricing.durationsWhole-minute price tiers keyed by source length.

elevenlabs-voice-changer supports: formats mp3, wav, ogg, mp4, aac; max source 300 s; noise removal and seed supported; the curated ElevenLabs voices (Aria default, Roger, Sarah, …) or any ElevenLabs Voice ID; output mp3. Read its price tiers from pricing.durations rather than hard-coding them.

Lifecycle

1. POST /audio/voice-changer/quote
bash
curl https://api.venice.ai/api/v1/audio/voice-changer/quote \
  -H "Content-Type: application/json" \
  -d '{ "model": "elevenlabs-voice-changer", "duration_seconds": 52 }'

Response: { "quote": <USD>, "duration_seconds": 52 }.

FieldNotes
modelRequired. A voice-changer model.
duration_secondsRequired. Positive integer or numeric string, ≤ max_source_audio_duration_seconds.

This is an estimate for the length you declare. The actual charge uses the length Venice measures when you queue; if both round up to the same whole minute the price is identical.

2. POST /audio/voice-changer/queue

Supply the source exactly once — a multipart file or a JSON audio_url. Both or neither → 400.

bash
# Upload
curl https://api.venice.ai/api/v1/audio/voice-changer/queue \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -F "model=elevenlabs-voice-changer" \
  -F "file=@take-03.wav" \
  -F "voice=Roger" \
  -F "remove_background_noise=true"

# By URL
curl https://api.venice.ai/api/v1/audio/voice-changer/queue \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "elevenlabs-voice-changer",
    "audio_url": "https://example.com/take-03.mp3",
    "voice": "Roger",
    "seed": 42
  }'

Response:

json
{ "model": "elevenlabs-voice-changer", "queue_id": "…", "status": "QUEUED", "duration_seconds": 52 }

duration_seconds is the source length measured server-side — the exact quantity billed.

FieldNotes
modelRequired.
fileMultipart source recording, max 25 MB.
audio_urlPublic http(s) URL. Venice fetches it (30 s timeout, 25 MB cap), validates the bytes, and forwards only the bytes — the URL itself is never passed to the provider.
voice1–60 chars. A curated voice or provider Voice ID. Defaults to default_voice. Not checked against voices at queue time — an unknown Voice ID fails with 400 at queue or on retrieve.
remove_background_noiseBoolean ("true" / "false" in multipart).
seedNon-negative integer, for reproducible output.

The body is strict — unknown fields → 400. Format, length, seed and balance are checked before you're charged. A voice the provider rejects at queue time returns 400, and any charge is refunded immediately.

Show full SKILL.md (435 more words)Show less
3. POST /audio/voice-changer/retrieve
bash
curl https://api.venice.ai/api/v1/audio/voice-changer/retrieve \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"elevenlabs-voice-changer","queue_id":"..."}' \
  --output converted.mp3
  • Still running: 200 {"status":"PROCESSING","average_execution_time":<ms>,"execution_duration":<ms since queued>}.
  • Done: 200 with the audio bytes, plus x-venice-audio-format, x-venice-inference-time (s), x-venice-model-id, x-venice-model-name, and x-venice-audio-duration when known.
  • Failed: an error status with { "error": "…", "credits_refunded": true|false }. If the provider accepted then failed the job, the charge is refunded; when credits_refunded is false, the message says whether anything is owed. The verdict is stored, so later polls return the same answer without a second refund.
  • delete_media_on_completion: true releases the provider copy as soon as the audio is returned.

The audio is delivered once. After a successful download, the next retrieve for that queue_id returns 404. Save the bytes on the first success.

4. POST /audio/voice-changer/complete
bash
curl https://api.venice.ai/api/v1/audio/voice-changer/complete \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"elevenlabs-voice-changer","queue_id":"..."}'

Returns {"success": true} once the provider-held media is released (false if the delete didn't go through). Safe to call more than once. Skip it if you retrieved with delete_media_on_completion: true.

Full loop (TypeScript)

ts
import fs from 'node:fs/promises'

const base = 'https://api.venice.ai/api/v1'
const auth = { Authorization: `Bearer ${process.env.VENICE_API_KEY}` }
const model = 'elevenlabs-voice-changer'

async function convert(path: string, voice: string) {
  const form = new FormData()
  form.append('model', model)
  form.append('voice', voice)
  form.append('file', new Blob([await fs.readFile(path)]), 'source.wav')

  const queued = await fetch(`${base}/audio/voice-changer/queue`, { method: 'POST', headers: auth, body: form })
  if (!queued.ok) throw new Error(`queue ${queued.status}: ${await queued.text()}`)
  const { queue_id, duration_seconds } = await queued.json()
  console.log('billed seconds:', duration_seconds)

  while (true) {
    const res = await fetch(`${base}/audio/voice-changer/retrieve`, {
      method: 'POST',
      headers: { ...auth, 'Content-Type': 'application/json' },
      body: JSON.stringify({ model, queue_id, delete_media_on_completion: true }),
    })
    if (!res.ok) throw new Error(`retrieve ${res.status}: ${await res.text()}`)
    if (!(res.headers.get('content-type') ?? '').startsWith('application/json')) {
      await fs.writeFile('converted.mp3', Buffer.from(await res.arrayBuffer()))
      return
    }
    await new Promise(r => setTimeout(r, 3000))
  }
}

Errors

CodeMeaning
400Strict-body error; both or neither of file / audio_url; audio_url unreachable or unusable; source not in accepted_audio_formats, has a video track, or its length can't be read; voice rejected by the provider (at queue, or later on retrieve — then refunded); non-voice-changer model; unknown / foreign queue_id ("Request ID is invalid.").
401Authentication failed.
402Insufficient balance (checked against the price for the measured length). Wallet callers above the $0.10 floor but below the price get the plain {"error":"Insufficient USD or Diem balance…"} body, not PAYMENT_REQUIRED.
403A PRIVATE_ONLY key calling an anonymized model, or region restriction.
404Model not found (today: every regular API key); on retrieve, media expired or already delivered.
413Uploaded file over 25 MB.
422Source longer than max_source_audio_duration_seconds (at queue, not charged); or, on retrieve, a provider content-policy rejection (refunded).
429Rate limited (40/min queue, 120/min retrieve, per user).
500Inference failure; body carries credits_refunded on retrieve.
503Model at capacity.
504On retrieve: the provider never accepted the job and it can no longer complete (after ~10 min); charge refunded.

See venice-errors for general body shapes.

Gotchas

  • Check availability first — see the note at the top. A 404 on quote with a correct model id means your key can't use it.
  • Billing is on the source length, measured server-side and rounded up to whole minutes. A 61 s clip costs the 2-minute tier; trim silence before uploading.
  • Don't blindly retry a queue call: a 200 means you've been charged. Keep the queue_id and poll instead.
  • Save the audio on the first successful retrieve — there's no second download.
  • Mislabelled files are fine (the bytes decide the format); a video file is rejected even if it's an MP4 with audio — extract the audio track first.

© veniceai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

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

Open the folder on GitHubat commit 5eaeac5

Compare with similar skills

Venice Audio Voice Changer 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 Voice Changer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Venice Audio Voice Changer this skillveniceai/skills144—~2.8kAutomated safety check: PassMIT
BlockrunBlockRunAI/blockrun-mcp391—~2.7kAutomated safety check: PassMIT
BlockRun Image GenerationBlockRunAI/ClawRouter6.6k—~2.1kAutomated safety check: PassMIT
Run402LeoYeAI/openclaw-master-skills2.2k—~4.8kAutomated safety check: PassMIT
Cap Cinematic Demo GeneratorCapSoftware/Cap23k—~2.4kAutomated safety check: PassCustom licence
Musictadaspetra/loop2962 repos~827Automated safety check: PassMIT

Similar skills

  • Blockrun

    BlockRunAI/blockrun-mcp

    Pay-per-call access to AI models, real-time data, media generation and multi-chain RPC over x402 micropayments (USDC on Base or Solana), or a BlockRun account API key.

    391 GitHub stars~2.7k tokensUpdated 3 days ago
    Media & CreativeAuto-check passed

  • BlockRun Image Generation

    BlockRunAI/ClawRouter

    Generates or edits images through ClawRouter's local image API, with a choice of models and sizes and payment handled automatically through x402.

    6.6k GitHub stars~2.1k tokensUpdated 5 days ago
    Media & CreativeAuto-check passed

  • Run402

    LeoYeAI/openclaw-master-skills

    Provision Postgres databases, deploy static sites, generate images, and build full-stack webapps on Run402 using x402 micropayments.

    2.2k GitHub stars~4.8k tokensUpdated 2 mo ago
    Backend & APIsAuto-check passed

  • Cap Cinematic Demo Generator

    CapSoftware/Cap

    Turns any URL into a short cinematic product-demo video on macOS, scouting the page, recording it with virtual input, then treating the clip with Cap's 3D camera and music.

    23k GitHub stars~2.4k tokensUpdated today
    Media & CreativeAuto-check passed

  • Music

    tadaspetra/loop

    Generate music using ElevenLabs Music API. An agent skill from tadaspetra/loop.

    296 GitHub starsUsed in 2 repos~827 tokens
    Media & CreativeAuto-check passed

  • Agentic Wallet

    coinbase/agentic-wallet-skills

    Crypto wallet operations via the awal CLI — sign in, check balances, send USDC/ETH/POL/SOL, trade tokens, fund the wallet, and use the x402 payment protocol to discover paid services, pay for API…

    126 GitHub starsUsed in 2 repos~1k tokens
    Backend & APIsAuto-check passed

More from veniceai/skills

All 22 skills in this repo

  • Venice Text Model Routing

    veniceai/skills

    Picks which Venice text model to call for a prompt based on privacy tier, input modality, capabilities and cost, and decides when to escalate from a local agent.

    144 GitHub stars~5.2k tokensUpdated 5 days ago
    Auto-check passed

  • Venice Models API

    veniceai/skills

    Documents Venice's model discovery endpoints, GET /models, /models/traits and /models/compatibility_mapping, so an agent can pick a model by capability, constraint or price.

    144 GitHub stars~4.3k tokensUpdated 5 days ago
    Auto-check passed

  • Venice API Keys

    veniceai/skills

    Manages Venice API keys through the /api_keys endpoints: create, list, update and revoke keys, set spending limits, and read rate limits.

    144 GitHub stars~3.8k tokensUpdated 5 days ago
    Auto-check passed

  • Venice API Overview

    veniceai/skills

    High-level map of the Venice.ai API: base URL, auth modes per endpoint, endpoint categories, response headers, pricing model, error shape and versioning.

    144 GitHub stars~3.5k tokensUpdated 5 days ago
    Auto-check passed

  • Venice Audio Music

    veniceai/skills

    Async music, sound-effect and long-form voice generation via Venice.

    144 GitHub stars~3.1k tokensUpdated 5 days ago
    Auto-check passed

  • Venice Audio Speech

    veniceai/skills

    Generate speech from text via POST /audio/speech, and clone a voice via POST /audio/voices.

    144 GitHub stars~3.6k tokensUpdated 5 days ago
    Auto-check passed

Works with

Categories

Questions about Venice Audio Voice Changer

What does Venice Audio Voice Changer do?

Async speech-to-speech voice conversion via Venice — re-record a source recording in a different voice while keeping delivery and timing. Venice Audio Voice Changer is an agent skill from veniceai/skills. Async speech-to-speech voice conversion via Venice — re-record a source recording in a different voice while keeping delivery and timing.

When should I use Venice Audio Voice Changer?

Venice Audio Voice Changer fits situations like: media & Creative work in your project.

How do I install Venice Audio Voice Changer in Claude Code?

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

How do I install Venice Audio Voice Changer in Codex?

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

Can I use Venice Audio Voice Changer 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-voice-changer -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-voice-changer, .gemini/skills/venice-audio-voice-changer, .github/skills/venice-audio-voice-changer and .opencode/skills/venice-audio-voice-changer in your project.

What does Venice Audio Voice Changer need to run?

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

Does Venice Audio Voice Changer 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 Voice Changer 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 Voice Changer use?

Venice Audio Voice Changer 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 Voice Changer use?

About 2.8k tokens (SKILL.md is roughly 11k 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 Voice Changer?

Skills that share tags, products or a category with Venice Audio Voice Changer: Blockrun (BlockRunAI/blockrun-mcp, 391 stars), BlockRun Image Generation (BlockRunAI/ClawRouter, 6.6k stars), Run402 (LeoYeAI/openclaw-master-skills, 2.2k stars) and Cap Cinematic Demo Generator (CapSoftware/Cap, 23k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Venice Audio Voice Changer?

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.