modesty-audiopod（谦虚的音频荚）

📖 Complete setup guide: https://skillboss.co/skill.md

SkillBoss Audio Processing

Full audio processing via SkillBoss API Hub: music generation, TTS, STT, stem separation, noise reduction, speaker separation.

Setup

import requests, os

SKILLBOSS_API_KEY = os.environ["SKILLBOSS_API_KEY"]
API_BASE = "https://api.skillboss.co/v1"

def pilot(body: dict) -> dict:
    r = requests.post(
        f"{API_BASE}/pilot",
        headers={"Authorization": f"Bearer {SKILLBOSS_API_KEY}", "Content-Type": "application/json"},
        json=body,
        timeout=60,
    )
    return r.json()

Auth: set SKILLBOSS_API_KEY env var. All requests use Authorization: Bearer $SKILLBOSS_API_KEY.

AI Music Generation

Generate songs, instrumentals, samples, and vocals from text prompts via SkillBoss API Hub.

Capabilities: music generation (full song with vocals), instrumental, rap, samples, audio-to-audio style transfer

Python

# Generate a full song
result = pilot({
    "type": "music",
    "inputs": {
        "prompt": "Upbeat pop, synth, drums, 120 bpm, female vocals, radio-ready",
        "lyrics": "Verse 1:\
Walking down the street on a sunny day\
\
Chorus:\
We're on fire tonight!",
        "duration": 60
    },
    "prefer": "quality"
})
audio_url = result["data"]["result"]["audio_url"]
print(audio_url)

# Generate instrumental (no lyrics needed)
result = pilot({
    "type": "music",
    "inputs": {
        "prompt": "Atmospheric ambient soundscape, uplifting, driving mood",
        "duration": 30
    },
    "prefer": "balanced"
})
audio_url = result["data"]["result"]["audio_url"]

# Generate rap
result = pilot({
    "type": "music",
    "inputs": {
        "prompt": "Lo-Fi Hip Hop, 100 BPM, male rap, melancholy, keyboard chords",
        "lyrics": "Verse 1:\
Started from the bottom, now we climbing...",
        "duration": 60,
        "style": "rap"
    },
    "prefer": "balanced"
})
audio_url = result["data"]["result"]["audio_url"]

# Generate samples/loops
result = pilot({
    "type": "music",
    "inputs": {
        "prompt": "drum loop, sad mood",
        "duration": 15,
        "style": "samples"
    },
    "prefer": "balanced"
})
audio_url = result["data"]["result"]["audio_url"]

cURL

# Generate full song
curl -X POST "https://api.skillboss.co/v1/pilot" \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"type":"music","inputs":{"prompt":"upbeat pop, synth, 120bpm, female vocals","lyrics":"Walking down the street...","duration":60},"prefer":"quality"}'

# Generate instrumental
curl -X POST "https://api.skillboss.co/v1/pilot" \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"type":"music","inputs":{"prompt":"ambient soundscape, uplifting","duration":30},"prefer":"balanced"}'

# Generate rap
curl -X POST "https://api.skillboss.co/v1/pilot" \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"type":"music","inputs":{"prompt":"Lo-Fi Hip Hop, male rap, 100 BPM","lyrics":"Started from the bottom...","duration":60,"style":"rap"}}'

# Generate samples
curl -X POST "https://api.skillboss.co/v1/pilot" \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"type":"music","inputs":{"prompt":"drum loop, sad mood","duration":15,"style":"samples"}}'

Parameters

Response

audio_url = result["data"]["result"]["audio_url"]

Stem Separation

Split audio into individual instrument/vocal tracks via SkillBoss API Hub audio routing.

Modes

Single stem options: vocals, drums, bass, guitar, piano, other

Python

# Extract stems from URL
result = pilot({
    "type": "audio",
    "capability": "stem separation",
    "inputs": {
        "url": "https://youtube.com/watch?v=VIDEO_ID",
        "mode": "six"
    },
    "prefer": "quality"
})
download_urls = result["data"]["result"]["download_urls"]
for stem, url in download_urls.items():
    print(f"{stem}: {url}")

# Extract from local file (base64-encoded)
import base64
audio_b64 = base64.b64encode(open("/path/to/song.mp3", "rb").read()).decode()
result = pilot({
    "type": "audio",
    "capability": "stem separation",
    "inputs": {
        "audio_data": audio_b64,
        "filename": "song.mp3",
        "mode": "four"
    },
    "prefer": "balanced"
})
download_urls = result["data"]["result"]["download_urls"]

# Single stem extraction
result = pilot({
    "type": "audio",
    "capability": "stem separation",
    "inputs": {
        "url": "https://youtube.com/watch?v=ID",
        "mode": "single",
        "stem": "vocals"
    },
    "prefer": "quality"
})
vocal_url = result["data"]["result"]["download_urls"]["vocals"]

cURL

# Extract stems from URL
curl -X POST "https://api.skillboss.co/v1/pilot" \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"type":"audio","capability":"stem separation","inputs":{"url":"https://youtube.com/watch?v=VIDEO_ID","mode":"six"},"prefer":"quality"}'

# Single stem
curl -X POST "https://api.skillboss.co/v1/pilot" \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"type":"audio","capability":"stem separation","inputs":{"url":"URL","mode":"single","stem":"vocals"}}'

Response Format

{
  "data": {
    "result": {
      "download_urls": {
        "vocals": "https://...",
        "drums": "https://...",
        "bass": "https://...",
        "other": "https://..."
      },
      "quality_scores": {
        "vocals": 0.95,
        "drums": 0.88
      }
    }
  }
}

Text to Speech

Generate speech from text with 50+ voices in 60+ languages via SkillBoss API Hub.

Python

# Generate speech
result = pilot({
    "type": "tts",
    "inputs": {
        "text": "Hello, world! This is a test.",
        "voice": "alloy",
        "speed": 1.0
    },
    "prefer": "balanced"
})
audio_url = result["data"]["result"]["audio_url"]
print(audio_url)

# Specify language
result = pilot({
    "type": "tts",
    "inputs": {
        "text": "Bonjour le monde",
        "voice": "alloy",
        "language": "fr",
        "speed": 1.0
    },
    "prefer": "quality"
})
audio_url = result["data"]["result"]["audio_url"]

cURL

# Generate speech
curl -X POST "https://api.skillboss.co/v1/pilot" \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"type":"tts","inputs":{"text":"Hello world, this is a test","voice":"alloy","speed":1.0},"prefer":"balanced"}'

Parameters

Response

audio_url = result["data"]["result"]["audio_url"]

Speaker Separation

Separate audio by speaker with automatic diarization via SkillBoss API Hub.

Python

# Diarize from file
import base64
audio_b64 = base64.b64encode(open("./meeting.mp3", "rb").read()).decode()
result = pilot({
    "type": "stt",
    "capability": "speaker diarization",
    "inputs": {
        "audio_data": audio_b64,
        "filename": "meeting.mp3",
        "num_speakers": 3
    },
    "prefer": "quality"
})
for segment in result["data"]["result"]["segments"]:
    print(f"Speaker {segment['speaker']}: {segment['text']} [{segment['start']:.1f}s - {segment['end']:.1f}s]")

# Diarize from URL
result = pilot({
    "type": "stt",
    "capability": "speaker diarization",
    "inputs": {
        "url": "https://youtube.com/watch?v=VIDEO_ID",
        "num_speakers": 2
    },
    "prefer": "balanced"
})
segments = result["data"]["result"]["segments"]

cURL

# Diarize from URL
curl -X POST "https://api.skillboss.co/v1/pilot" \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"type":"stt","capability":"speaker diarization","inputs":{"url":"https://youtube.com/watch?v=VIDEO_ID","num_speakers":2},"prefer":"balanced"}'

Speech to Text (Transcription)

Transcribe audio/video with speaker diarization, word-level timestamps, and multiple output formats via SkillBoss API Hub.

Python

# Transcribe from URL
result = pilot({
    "type": "stt",
    "inputs": {
        "url": "https://youtube.com/watch?v=VIDEO_ID",
        "speaker_diarization": True,
        "word_timestamps": True
    },
    "prefer": "balanced"
})
text = result["data"]["result"]["text"]
segments = result["data"]["result"].get("segments", [])
print(f"Transcript: {text}")
for seg in segments:
    print(f"[{seg.get('start', 0):.1f}s] {seg.get('speaker','?')}: {seg['text']}")

# Transcribe local file
import base64
audio_b64 = base64.b64encode(open("./recording.mp3", "rb").read()).decode()
result = pilot({
    "type": "stt",
    "inputs": {
        "audio_data": audio_b64,
        "filename": "recording.mp3",
        "language": "en",
        "speaker_diarization": True
    },
    "prefer": "balanced"
})
text = result["data"]["result"]["text"]

cURL

# Transcribe from URL
curl -X POST "https://api.skillboss.co/v1/pilot" \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"type":"stt","inputs":{"url":"https://youtube.com/watch?v=ID","speaker_diarization":true,"word_timestamps":true},"prefer":"balanced"}'

Parameters

Response

text = result["data"]["result"]["text"]
segments = result["data"]["result"].get("segments", [])  # with speaker_diarization

Noise Reduction

Remove background noise from audio files via SkillBoss API Hub.

Python

# Denoise from file
import base64
audio_b64 = base64.b64encode(open("./noisy-audio.mp3", "rb").read()).decode()
result = pilot({
    "type": "audio",
    "capability": "noise reduction",
    "inputs": {
        "audio_data": audio_b64,
        "filename": "noisy-audio.mp3"
    },
    "prefer": "quality"
})
clean_url = result["data"]["result"]["audio_url"]
print(f"Clean audio: {clean_url}")

# Denoise from URL
result = pilot({
    "type": "audio",
    "capability": "noise reduction",
    "inputs": {
        "url": "https://example.com/noisy.mp3"
    },
    "prefer": "balanced"
})
clean_url = result["data"]["result"]["audio_url"]

cURL

# Denoise from URL
curl -X POST "https://api.skillboss.co/v1/pilot" \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"type":"audio","capability":"noise reduction","inputs":{"url":"https://example.com/noisy.mp3"},"prefer":"quality"}'

Response

clean_url = result["data"]["result"]["audio_url"]

Chain Mode (Multi-step Workflow)

Use SkillBoss Chain mode to combine multiple audio steps in one call.

Python

# STT → Chat (summarize) → TTS pipeline
result = pilot({
    "chain": [
        {"type": "stt"},
        {"type": "chat", "capability": "summarize"},
        {"type": "tts"}
    ]
})

# Transcribe and translate
result = pilot({
    "chain": [
        {"type": "stt"},
        {"type": "chat", "capability": "translate to English"}
    ]
})

API Endpoint Summary

All capabilities route through a single endpoint:

Single endpoint: POST https://api.skillboss.co/v1/pilot Auth: Authorization: Bearer $SKILLBOSS_API_KEY

Response Format Summary