Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
bytedance avatar

Byted Tos Audio Process

  • 8 installs
  • 411 repo stars
  • Updated August 4, 2026
  • bytedance/agentkit-samples

byted-tos-audio-process is a Claude skill that converts audio objects in Volcengine TOS into PCM-oriented WAV output through TOS media_jobs async jobs.

About

This skill converts audio objects stored in Volcengine TOS into PCM-oriented WAV output using TOS data-process async jobs. A developer uses it to resample audio to 16k, convert to mono, change sample format, and normalize audio to prepare files for speech-recognition pipelines. It submits async jobs through the TOS gateway media_jobs API and can poll until completion.

  • Converts TOS-stored audio to PCM-oriented WAV via async media jobs
  • Resamples to 16k, converts to mono, and changes sample format for ASR
  • Runs as async jobs with a --wait poll flag

Byted Tos Audio Process by the numbers

  • 8 all-time installs (skills.sh)
  • Ranked #1,072 of 1,335 Generative Media skills by installs in the Skillselion catalog
  • Data as of Aug 5, 2026 (Skillselion catalog sync)
At a glance

byted-tos-audio-process capabilities & compatibility

Requires Volcengine TOS credentials (access key, secret, endpoint, region, bucket)

Capabilities
audio conversion · media processing · asr preprocessing
Use cases
transcription
Pricing
Bring your own API key
From the docs

What byted-tos-audio-process says it does

Converts audio objects stored in Volcengine TOS into PCM-oriented WAV output through TOS data-process async jobs.
SKILL.md
This skill uses the TOS gateway's `media_jobs` API with `job_type=AudioConvert`.
SKILL.md
npx skills add https://github.com/bytedance/agentkit-samples --skill byted-tos-audio-process

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs8
repo stars411
Last updatedAugust 4, 2026
Repositorybytedance/agentkit-samples

What it does

Convert Volcengine TOS audio objects to 16k mono PCM WAV to prepare files for ASR pipelines.

When should I use this skill?

You need to convert TOS audio to PCM or WAV, resample to 16k, convert to mono, or normalize audio for a speech-recognition pipeline.

What you get

Submits an AudioConvert job that outputs a PCM-oriented WAV file to TOS, optionally waiting for completion.

By the numbers

  • Bundles 2 scripts (audio_to_pcm.py, tos_jobs_client.py)
  • Default example outputs 16k mono s16 WAV

Files

SKILL.mdMarkdownGitHub ↗

Volcengine TOS Audio Process

Convert audio files stored in Volcengine TOS into PCM-oriented WAV output through the TOS gateway's media_jobs API.

Setup (once per environment)

Install dependencies on first use:

cd {baseDir}
pip install -r {baseDir}/requirements.txt

Then run scripts with Python 3.7+:

python3 {baseDir}/scripts/<script>.py <args>

Environment Variables

This skill relies on the TOS identity declared in the metadata block. Common runtime variables are:

Environment VariableRequiredDescription
TOS_ACCESS_KEYYesTOS access key ID
TOS_SECRET_KEYYesTOS secret access key
TOS_ENDPOINTYesTOS endpoint URL
TOS_REGIONYesTOS region
TOS_BUCKETYesSource bucket that stores the audio object
TOS_OBJECT_KEYNoSource object key of the audio file. Can be overridden with --key
TOS_SECURITY_TOKENNoSTS session token when using temporary credentials

Quick start

# Convert an audio object to 16k mono s16 WAV and wait for completion
python3 {baseDir}/scripts/audio_to_pcm.py \
  --key test.wav \
  --sample-rate 16000 \
  --channels 1 \
  --sample-format s16 \
  --output-object skill-test/audio/test_pcm.wav \
  --wait

Available scripts

ScriptPurpose
scripts/audio_to_pcm.pySubmit an async AudioConvert job via the TOS gateway's media_jobs API that converts TOS audio into PCM-oriented WAV output. Supports --wait to poll until completion.
scripts/tos_jobs_client.pyShared client for TOS gateway doc_jobs/media_jobs APIs using pre-signed URL auth.

Rules

  • TOS gateway API: This skill uses the TOS gateway's media_jobs API with job_type=AudioConvert. Authentication is handled via pre_signed_url from the TOS Python SDK and the TOS identity declared in the metadata block above.
  • Current output format: The output is a WAV file (PCM container), not raw headerless .pcm bytes.
  • Async job model: The script creates async jobs and optionally waits for completion with the --wait flag.
  • Language: Reply in the user's preferred language.

Further reading

  • Setup and environment: README.md
  • Parameter reference: REFERENCE.md
  • End-to-end workflows: WORKFLOWS.md

Related skills

Generative Mediaintegrationsbackend

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.