Audio Synthesis Pipelines

from elevenlabs.client import ElevenLabs

client = ElevenLabs(api_key="YOUR_KEY")

# Multi-turn, emotional narration
audio_stream = client.text_to_speech.convert_as_stream(
    voice_id="21m00Tcm4TlvDq8ikWAM",
    model_id="eleven_v3",
    text="[whispering] Nobody knows what's behind the door. [excited] But today, we find out!",
    voice_settings={
        "stability": 0.4,     # lower = more expressive
        "similarity_boost": 0.75,
        "style": 0.5,         # higher = more emotional
        "use_speaker_boost": True,
    },
    output_format="mp3_44100_128",
)

with open("narration.mp3", "wb") as f:
    for chunk in audio_stream:
        f.write(chunk)

# Streaming = start playback before full generation completes
# Critical for conversational apps (sub-500ms first-chunk latency with v3)

import requests

# Stable Audio 2 via Stability AI API
resp = requests.post(
    "https://api.stability.ai/v2beta/audio/stable-audio-2/generate",
    headers={"Authorization": f"Bearer {STABILITY_KEY}"},
    files={"none": ""},
    data={
        "prompt": "Heavy wooden door creaking open in a stone hallway, reverberant, dramatic",
        "duration": 6,       # seconds
        "steps": 50,
        "cfg_scale": 7,
        "output_format": "mp3",
        "seed": 42,
    },
)
with open("sfx_door.mp3", "wb") as f:
    f.write(resp.content)

# Stable Audio 2: strong at SFX and short musical loops up to ~3 min

import requests

# Suno API (via partner providers like api.box / suno.ai developer portal)
resp = requests.post(
    "https://api.suno.ai/v1/songs",
    headers={"Authorization": f"Bearer {SUNO_KEY}"},
    json={
        "prompt": "Upbeat indie-folk with ukulele, handclaps, joyful female lead",
        "lyrics": "[Verse]\nMorning comes slow in this little town\n[Chorus]\nWe rise / we rise / we rise with the sun",
        "model": "suno-v5",
        "duration": 120,
        "instrumental": False,
    },
)
job_id = resp.json()["id"]
# Suno is async — poll job status. Returns two stereo 48kHz MP3s typically.

from pydub import AudioSegment

# Load assets
narration = AudioSegment.from_mp3("narration.mp3")
sfx_door = AudioSegment.from_mp3("sfx_door.mp3")
music_bed = AudioSegment.from_mp3("music_bed.mp3")

# Duck the music under narration (common broadcast technique)
music_ducked = music_bed - 12  # -12 dB under narration

# Build the timeline
output = AudioSegment.silent(duration=0)
output += music_ducked[:3000]                              # 3s music intro
output = output.overlay(narration, position=3000)          # narration starts at 3s
output = output.overlay(sfx_door, position=5500)           # door SFX at 5.5s
output += music_bed[len(output):len(output)+2000]          # 2s music outro

# Normalize to broadcast standard
from pydub.effects import normalize
final = normalize(output)
final.export("scene_1_mix.mp3", format="mp3", bitrate="192k")