인터페이스는 현지화되어 있으며, Skill 소개와 설명 문서는 선택한 언어로 AI가 자동 번역합니다. 코드·명령어·경로·전문 용어는 원문을 유지하며 원작자 문서가 우선합니다.
Skills 둘러보기
데이터 및 연구 · SKILL.md

byted-tos-audio-process

byted-tos-audio-process

Converts audio objects stored in Volcengine TOS into PCM-oriented WAV output through TOS data-process async jobs. Use this skill when the user needs to convert audio to PCM or WAV, resample audio to 16k, convert to mono, change sample format, normalize audio for ASR pipelines, or prepare TOS audio files for speech recognition — even if they don't explicitly…

Independent GitHub snapshot · Automated classification · Original documentation governs

Skill 문서

GitHub

name: byted-tos-audio-process description: "Converts audio objects stored in Volcengine TOS into PCM-oriented WAV output through TOS data-process async jobs. Use this skill when the user needs to convert audio to PCM or WAV, resample audio to 16k, convert to mono, change sample format, normalize audio for ASR pipelines, or prepare TOS audio files for speech recognition — even if they don't explicitly mention 'PCM' or 'audio conversion'." metadata: version: "1.0.0" openclaw: identity: - type: apikey provider: tos_provider env: - TOS_ACCESS_KEY - TOS_SECRET_KEY - TOS_ENDPOINT - TOS_REGION - TOS_BUCKET required: true optional: env: - TOS_OBJECT_KEY - TOS_SECURITY_TOKEN user-invocable: true license: Apache-2.0

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

저장한 Skills