elevenlabs

from elevenlabs.client import ElevenLabs
from elevenlabs import save, VoiceSettings
import os

client = ElevenLabs(api_key=os.getenv("ELEVENLABS_API_KEY"))

audio = client.text_to_speech.convert(
    text="Welcome to my video!",
    voice_id="JBFqnCBsd6RMkjVDRZzb",
    model_id="eleven_multilingual_v2",
    voice_settings=VoiceSettings(
        stability=0.5,
        similarity_boost=0.75,
        style=0.5,
        speed=1.0
    )
)
save(audio, "voiceover.mp3")

from elevenlabs import DialogueInput

audio = client.text_to_dialogue.convert(
    inputs=[DialogueInput(text="[warm] Welcome to my video!", voice_id="JBFqnCBsd6RMkjVDRZzb")],
    model_id="eleven_v4",
    settings={"stability": 0.5, "similarity": 0.75},  # the only two settings v4 takes
)
save(audio, "voiceover.mp3")

...end of section. <break time="1.5s" /> Start of next...

<phoneme alphabet="ipa" ph="ˈdʒeɪnəs">Janus</phoneme>

The term "/ˌbaɪoʊˈkemɪstri/" refers to the study of chemical processes.

with open("voiceover.mp3", "rb") as f:
    result = client.speech_to_text.convert(file=f, model_id="scribe_v2", tag_audio_events=False)
words = [w for w in result.words if w.type == "word"]  # .text, .start, .end (seconds)

with open("sample.mp3", "rb") as f:
    voice = client.voices.ivc.create(
        name="My Voice",
        files=[f],
        remove_background_noise=True
    )
print(f"Voice ID: {voice.voice_id}")

result = client.text_to_sound_effects.convert(
    text="Thunder rumbling followed by heavy rain",
    duration_seconds=10,
    prompt_influence=0.3
)
with open("thunder.mp3", "wb") as f:
    for chunk in result:
        f.write(chunk)

result = client.music.compose(
    prompt="Upbeat indie rock, catchy guitar riff, energetic drums, travel vlog",
    music_length_ms=60000,
    force_instrumental=True
)
with open("music.mp3", "wb") as f:
    for chunk in result:
        f.write(chunk)

VOICEOVER-SCRIPT.md → voiceover.py → public/audio/ → Remotion composition
        ↓                  ↓               ↓                 ↓
  Scene narration    Generate MP3    Audio files     <Audio> component
  with durations     per scene       with timing     synced to scenes

# Generate voiceover files for each scene
uv run tools/voiceover.py --scene-dir public/audio/scenes --json

# Output:
# public/audio/scenes/
#   ├── scene-01-title.mp3
#   ├── scene-02-problem.mp3
#   ├── scene-03-solution.mp3
#   └── manifest.json  (durations for each file)

{
  "scenes": [
    { "file": "scene-01-title.mp3", "duration": 4.2 },
    { "file": "scene-02-problem.mp3", "duration": 12.8 },
    { "file": "scene-03-solution.mp3", "duration": 15.3 }
  ],
  "totalDuration": 32.3
}

// src/Composition.tsx
import { Audio, staticFile, Series, useVideoConfig } from 'remotion';

// Import scene components
import { TitleSlide } from './scenes/TitleSlide';
import { ProblemSlide } from './scenes/ProblemSlide';
import { SolutionSlide } from './scenes/SolutionSlide';

// Scene durations (from manifest.json, converted to frames at 30fps)
const SCENE_DURATIONS = {
  title: Math.ceil(4.2 * 30),      // 126 frames
  problem: Math.ceil(12.8 * 30),   // 384 frames
  solution: Math.ceil(15.3 * 30),  // 459 frames
};

export const MainComposition: React.FC = () => {
  return (
    <>
      {/* Scene sequence */}
      <Series>
        <Series.Sequence durationInFrames={SCENE_DURATIONS.title}>
          <TitleSlide />
        </Series.Sequence>
        <Series.Sequence durationInFrames={SCENE_DURATIONS.problem}>
          <ProblemSlide />
        </Series.Sequence>
        <Series.Sequence durationInFrames={SCENE_DURATIONS.solution}>
          <SolutionSlide />
        </Series.Sequence>
      </Series>

      {/* Audio track - plays continuously across all scenes */}
      <Audio src={staticFile('audio/voiceover.mp3')} volume={1} />

      {/* Optional: Background music at lower volume */}
      <Audio src={staticFile('audio/music.mp3')} volume={0.15} />
    </>
  );
};

// src/scenes/ProblemSlide.tsx
import { Audio, staticFile, useCurrentFrame } from 'remotion';

export const ProblemSlide: React.FC = () => {
  const frame = useCurrentFrame();

  return (
    <div style={{ /* slide styles */ }}>
      <h1>The Problem</h1>
      {/* Scene content */}

      {/* Audio starts when this scene starts (frame 0 of this sequence) */}
      <Audio src={staticFile('audio/scenes/scene-02-problem.mp3')} />
    </div>
  );
};

// src/config/timing.ts
import manifest from '../../public/audio/scenes/manifest.json';

const FPS = 30;

// Convert audio durations to frame counts
export const sceneDurations = manifest.scenes.reduce((acc, scene) => {
  const name = scene.file.replace(/^scene-\d+-/, '').replace('.mp3', '');
  acc[name] = Math.ceil(scene.duration * FPS);
  return acc;
}, {} as Record<string, number>);

// Usage in composition:
// <Series.Sequence durationInFrames={sceneDurations.title}>

import { Audio, Sequence, interpolate, useCurrentFrame } from 'remotion';

// Fade in audio
export const FadeInAudio: React.FC<{ src: string; fadeFrames?: number }> = ({
  src,
  fadeFrames = 30
}) => {
  const frame = useCurrentFrame();
  const volume = interpolate(frame, [0, fadeFrames], [0, 1], {
    extrapolateRight: 'clamp',
  });
  return <Audio src={src} volume={volume} />;
};

// Delayed audio start
export const DelayedAudio: React.FC<{ src: string; delayFrames: number }> = ({
  src,
  delayFrames
}) => (
  <Sequence from={delayFrames}>
    <Audio src={src} />
  </Sequence>
);

// Usage:
// <FadeInAudio src={staticFile('audio/music.mp3')} fadeFrames={60} />
// <DelayedAudio src={staticFile('audio/sfx/whoosh.mp3')} delayFrames={45} />

import { Audio, OffthreadVideo, staticFile, useVideoConfig } from 'remotion';

export const DemoScene: React.FC = () => {
  const { durationInFrames, fps } = useVideoConfig();

  // Calculate playback rate to fit demo into voiceover duration
  const demoDuration = 45; // seconds (original demo length)
  const sceneDuration = durationInFrames / fps; // seconds (from voiceover)
  const playbackRate = demoDuration / sceneDuration;

  return (
    <>
      <OffthreadVideo
        src={staticFile('demos/feature-demo.mp4')}
        playbackRate={playbackRate}
      />
      <Audio src={staticFile('audio/scenes/scene-04-demo.mp3')} />
    </>
  );
};

import { Audio, staticFile, delayRender, continueRender } from 'remotion';
import { useEffect, useState } from 'react';

export const SafeAudio: React.FC<{ src: string }> = ({ src }) => {
  const [handle] = useState(() => delayRender());
  const [audioReady, setAudioReady] = useState(false);

  useEffect(() => {
    const audio = new window.Audio(src);
    audio.oncanplaythrough = () => {
      setAudioReady(true);
      continueRender(handle);
    };
    audio.onerror = () => {
      console.error(`Failed to load audio: ${src}`);
      continueRender(handle); // Continue without audio rather than hang
    };
  }, [src, handle]);

  if (!audioReady) return null;
  return <Audio src={src} />;
};

/generate-voiceover

1. Reads VOICEOVER-SCRIPT.md
2. Extracts narration for each scene
3. Generates audio via ElevenLabs API
4. Saves to public/audio/scenes/
5. Creates manifest.json with durations
6. Updates project.json with timing info