Audiopod

pip install audiopod  # Python
npm install audiopod  # Node.js

from audiopod import AudioPod
client = AudioPod()  # uses AUDIOPOD_API_KEY env var
# or: client = AudioPod(api_key="ap_...")

# Generate a full song with lyrics
result = client.music.song(
    prompt="Upbeat pop, synth, drums, 120 bpm, female vocals, radio-ready",
    lyrics="Verse 1:\nWalking down the street on a sunny day\n\nChorus:\nWe're on fire tonight!",
    duration=60
)
print(result["output_url"])

# Generate rap
result = client.music.rap(
    prompt="Lo-Fi Hip Hop, 100 BPM, male rap, melancholy, keyboard chords",
    lyrics="Verse 1:\nStarted from the bottom, now we climbing...",
    duration=60
)

# Generate instrumental (no lyrics needed)
result = client.music.instrumental(
    prompt="Atmospheric ambient soundscape, uplifting, driving mood",
    duration=30
)

# Generic generate with explicit task
result = client.music.generate(
    prompt="Electronic dance music, high energy",
    task="text2samples",  # any task type
    duration=30
)

# Async: submit then poll
job = client.music.create(
    prompt="Chill lofi beat", 
    duration=30, 
    task="prompt2instrumental"
)
result = client.music.wait_for_completion(job["id"], timeout=600)

# Get available genre presets
presets = client.music.get_presets()

# List/manage jobs
jobs = client.music.list(skip=0, limit=50)
job = client.music.get(job_id=123)
client.music.delete(job_id=123)

# Song with lyrics
curl -X POST "https://api.audiopod.ai/api/v1/music/text2music" \
  -H "X-API-Key: $AUDIOPOD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"upbeat pop, synth, 120bpm, female vocals", "lyrics":"Walking down the street...", "audio_duration":60}'

# Rap
curl -X POST "https://api.audiopod.ai/api/v1/music/text2rap" \
  -H "X-API-Key: $AUDIOPOD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"Lo-Fi Hip Hop, male rap, 100 BPM", "lyrics":"Started from the bottom...", "audio_duration":60}'

# Instrumental
curl -X POST "https://api.audiopod.ai/api/v1/music/prompt2instrumental" \
  -H "X-API-Key: $AUDIOPOD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"ambient soundscape, uplifting", "audio_duration":30}'

# Samples/loops
curl -X POST "https://api.audiopod.ai/api/v1/music/text2samples" \
  -H "X-API-Key: $AUDIOPOD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"drum loop, sad mood", "audio_duration":15}'

# Vocals only
curl -X POST "https://api.audiopod.ai/api/v1/music/lyric2vocals" \
  -H "X-API-Key: $AUDIOPOD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"clean vocals, happy", "lyrics":"Eternal chorus of unity...", "audio_duration":30}'

# Check job status / get result
curl "https://api.audiopod.ai/api/v1/music/jobs/JOB_ID" \
  -H "X-API-Key: $AUDIOPOD_API_KEY"

# Get genre presets
curl "https://api.audiopod.ai/api/v1/music/presets" \
  -H "X-API-Key: $AUDIOPOD_API_KEY"

# List jobs
curl "https://api.audiopod.ai/api/v1/music/jobs?skip=0&limit=50" \
  -H "X-API-Key: $AUDIOPOD_API_KEY"

# Delete job
curl -X DELETE "https://api.audiopod.ai/api/v1/music/jobs/JOB_ID" \
  -H "X-API-Key: $AUDIOPOD_API_KEY"

# Sync: extract and wait for result
result = client.stems.separate(
    url="https://youtube.com/watch?v=VIDEO_ID",
    mode="six",
    timeout=600
)
for stem, url in result["download_urls"].items():
    print(f"{stem}: {url}")

# From local file
result = client.stems.separate(file="/path/to/song.mp3", mode="four")

# Single stem extraction
result = client.stems.separate(
    url="https://youtube.com/watch?v=ID",
    mode="single",
    stem="vocals"
)

# Async: submit then poll
job = client.stems.extract(url="https://youtube.com/watch?v=ID", mode="six")
print(f"Job ID: {job['id']}")
status = client.stems.status(job["id"])
# or wait:
result = client.stems.wait_for_completion(job["id"], timeout=600)

# List available modes
modes = client.stems.modes()

# Job management
jobs = client.stems.list(skip=0, limit=50, status="COMPLETED")
job = client.stems.get(job_id=1234)
client.stems.delete(job_id=1234)

# Extract from URL
curl -X POST "https://api.audiopod.ai/api/v1/stem-extraction/api/extract" \
  -H "X-API-Key: $AUDIOPOD_API_KEY" \
  -F "url=https://youtube.com/watch?v=VIDEO_ID" \
  -F "mode=six"

# Extract from file
curl -X POST "https://api.audiopod.ai/api/v1/stem-extraction/api/extract" \
  -H "X-API-Key: $AUDIOPOD_API_KEY" \
  -F "file=@/path/to/song.mp3" \
  -F "mode=four"

# Single stem
curl -X POST "https://api.audiopod.ai/api/v1/stem-extraction/api/extract" \
  -H "X-API-Key: $AUDIOPOD_API_KEY" \
  -F "url=URL" \
  -F "mode=single" \
  -F "stem=vocals"

# Check job status
curl "https://api.audiopod.ai/api/v1/stem-extraction/status/JOB_ID" \
  -H "X-API-Key: $AUDIOPOD_API_KEY"

# List available modes
curl "https://api.audiopod.ai/api/v1/stem-extraction/modes" \
  -H "X-API-Key: $AUDIOPOD_API_KEY"

# List jobs (filter by status: PENDING, PROCESSING, COMPLETED, FAILED)
curl "https://api.audiopod.ai/api/v1/stem-extraction/jobs?skip=0&limit=50&status=COMPLETED" \
  -H "X-API-Key: $AUDIOPOD_API_KEY"

# Get specific job
curl "https://api.audiopod.ai/api/v1/stem-extraction/jobs/JOB_ID" \
  -H "X-API-Key: $AUDIOPOD_API_KEY"

# Delete job
curl -X DELETE "https://api.audiopod.ai/api/v1/stem-extraction/jobs/JOB_ID" \
  -H "X-API-Key: $AUDIOPOD_API_KEY"

{
  "id": 1234,
  "status": "COMPLETED",
  "download_urls": {
    "vocals": "https://...",
    "drums": "https://...",
    "bass": "https://...",
    "other": "https://..."
  },
  "quality_scores": {
    "vocals": 0.95,
    "drums": 0.88
  }
}

# Generate speech and wait for result
result = client.voice.generate(
    text="Hello, world! This is a test.",
    voice_id=123,
    speed=1.0
)
print(result["output_url"])

# Async: submit then poll
job = client.voice.speak(
    text="Hello world",
    voice_id=123,
    speed=1.0
)
status = client.voice.get_job(job["id"])
result = client.voice.wait_for_completion(job["id"], timeout=300)

# List all available voices
voices = client.voice.list()
for v in voices:
    print(f"{v['id']}: {v['name']}")

# Clone a voice (needs ~5 sec audio sample)
new_voice = client.voice.create(
    name="My Voice Clone",
    audio_file="./sample.mp3",
    description="Cloned from recording"
)

# Get/delete voice
voice = client.voice.get(voice_id=123)
client.voice.delete(voice_id=123)

# List all voices
curl "https://api.audiopod.ai/api/v1/voice/voice-profiles" \
  -H "X-API-Key: $AUDIOPOD_API_KEY"

# Generate speech (FORM DATA, not JSON!)
curl -X POST "https://api.audiopod.ai/api/v1/voice/voices/{VOICE_UUID}/generate" \
  -H "Authorization: Bearer $AUDIOPOD_API_KEY" \
  -d "input_text=Hello world, this is a test" \
  -d "audio_format=mp3" \
  -d "speed=1.0"

# Poll job status
curl "https://api.audiopod.ai/api/v1/voice/tts-jobs/{JOB_ID}/status" \
  -H "Authorization: Bearer $AUDIOPOD_API_KEY"

# SDK-style endpoints (alternative)
# Generate via SDK endpoint
curl -X POST "https://api.audiopod.ai/api/v1/voice/tts/generate" \
  -H "X-API-Key: $AUDIOPOD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text":"Hello world","voice_id":123,"speed":1.0}'

# Poll via SDK endpoint
curl "https://api.audiopod.ai/api/v1/voice/tts/status/JOB_ID" \
  -H "X-API-Key: $AUDIOPOD_API_KEY"

# List voices (SDK endpoint)
curl "https://api.audiopod.ai/api/v1/voice/voices" \
  -H "X-API-Key: $AUDIOPOD_API_KEY"

# Clone a voice
curl -X POST "https://api.audiopod.ai/api/v1/voice/voices" \
  -H "X-API-Key: $AUDIOPOD_API_KEY" \
  -F "name=My Voice" \
  -F "file=@sample.mp3" \
  -F "description=Cloned voice"

# Delete voice
curl -X DELETE "https://api.audiopod.ai/api/v1/voice/voices/VOICE_ID" \
  -H "X-API-Key: $AUDIOPOD_API_KEY"

// Generate response
{"job_id": 12345, "status": "pending", "credits_reserved": 25}

// Status response (completed)
{"status": "completed", "output_url": "https://r2-url/generated.mp3"}

# Diarize and wait for result
result = client.speaker.identify(
    file="./meeting.mp3",
    num_speakers=3,  # optional hint for accuracy
    timeout=600
)
for segment in result["segments"]:
    print(f"Speaker {segment['speaker']}: {segment['text']} [{segment['start']:.1f}s - {segment['end']:.1f}s]")

# From URL
result = client.speaker.identify(
    url="https://youtube.com/watch?v=VIDEO_ID",
    num_speakers=2
)

# Async: submit then poll
job = client.speaker.diarize(
    file="./meeting.mp3",
    num_speakers=3
)
result = client.speaker.wait_for_completion(job["id"], timeout=600)

# Job management
jobs = client.speaker.list(skip=0, limit=50, status="COMPLETED")
job = client.speaker.get(job_id=123)
client.speaker.delete(job_id=123)

# Diarize from file
curl -X POST "https://api.audiopod.ai/api/v1/speaker/diarize" \
  -H "X-API-Key: $AUDIOPOD_API_KEY" \
  -F "file=@meeting.mp3" \
  -F "num_speakers=3"

# Diarize from URL
curl -X POST "https://api.audiopod.ai/api/v1/speaker/diarize" \
  -H "X-API-Key: $AUDIOPOD_API_KEY" \
  -F "url=https://youtube.com/watch?v=VIDEO_ID" \
  -F "num_speakers=2"

# Check job status
curl "https://api.audiopod.ai/api/v1/speaker/jobs/JOB_ID" \
  -H "X-API-Key: $AUDIOPOD_API_KEY"

# List jobs
curl "https://api.audiopod.ai/api/v1/speaker/jobs?skip=0&limit=50" \
  -H "X-API-Key: $AUDIOPOD_API_KEY"

# Delete job
curl -X DELETE "https://api.audiopod.ai/api/v1/speaker/jobs/JOB_ID" \
  -H "X-API-Key: $AUDIOPOD_API_KEY"

# Transcribe URL and wait
result = client.transcription.transcribe(
    url="https://youtube.com/watch?v=VIDEO_ID",
    speaker_diarization=True,
    min_speakers=2,
    max_speakers=5,
    timeout=600
)
print(f"Language: {result['detected_language']}")
for seg in result["segments"]:
    print(f"[{seg['start']:.1f}s] {seg.get('speaker','?')}: {seg['text']}")

# Batch: multiple URLs at once
result = client.transcription.transcribe(
    urls=["https://youtube.com/watch?v=ID1", "https://youtube.com/watch?v=ID2"],
    speaker_diarization=True
)

# Upload local file
job = client.transcription.upload(
    file_path="./recording.mp3",
    language="en",
    speaker_diarization=True
)
result = client.transcription.wait_for_completion(job["id"], timeout=600)

# Async: submit then poll
job = client.transcription.create(
    url="https://youtube.com/watch?v=ID",
    language="en",
    speaker_diarization=True,
    word_timestamps=True,
    min_speakers=2,
    max_speakers=4
)
result = client.transcription.wait_for_completion(job["id"], timeout=600)

# Get transcript in different formats
transcript_json = client.transcription.get_transcript(job_id=123, format="json")
transcript_srt = client.transcription.get_transcript(job_id=123, format="srt")
transcript_vtt = client.transcription.get_transcript(job_id=123, format="vtt")
transcript_txt = client.transcription.get_transcript(job_id=123, format="txt")

# Job management
jobs = client.transcription.list(skip=0, limit=50, status="COMPLETED")
job = client.transcription.get(job_id=123)
client.transcription.delete(job_id=123)

# Transcribe from URL
curl -X POST "https://api.audiopod.ai/api/v1/transcribe/transcribe" \
  -H "X-API-Key: $AUDIOPOD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"url":"https://youtube.com/watch?v=ID","enable_speaker_diarization":true,"word_timestamps":true}'

# Transcribe multiple URLs
curl -X POST "https://api.audiopod.ai/api/v1/transcribe/transcribe" \
  -H "X-API-Key: $AUDIOPOD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"urls":["URL1","URL2"],"enable_speaker_diarization":true}'

# Upload file for transcription
curl -X POST "https://api.audiopod.ai/api/v1/transcribe/transcribe-upload" \
  -H "X-API-Key: $AUDIOPOD_API_KEY" \
  -F "files=@recording.mp3" \
  -F "language=en" \
  -F "enable_speaker_diarization=true"

# Get job status
curl "https://api.audiopod.ai/api/v1/transcribe/jobs/JOB_ID" \
  -H "X-API-Key: $AUDIOPOD_API_KEY"

# Get transcript in specific format (json, srt, vtt, txt)
curl "https://api.audiopod.ai/api/v1/transcribe/jobs/JOB_ID/transcript?format=srt" \
  -H "X-API-Key: $AUDIOPOD_API_KEY"

# List jobs
curl "https://api.audiopod.ai/api/v1/transcribe/jobs?offset=0&limit=50" \
  -H "X-API-Key: $AUDIOPOD_API_KEY"

# Delete job
curl -X DELETE "https://api.audiopod.ai/api/v1/transcribe/jobs/JOB_ID" \
  -H "X-API-Key: $AUDIOPOD_API_KEY"