elevenlabs

What the source does

• FilesystemNone observedNo reads or writes in the source
• NetworkNone observedNo outbound calls in the source
• ShellNone observedNo commands run in the source
• DependenciesPinnedNothing floats
• SecretsNone foundNo keys in source

Five audit layers

Gates applied: instruction override, no behavioural pass.

- In a shared installation, never tell the user to create a `.env`, export a

Audit 0.4.1 · source sha cab239da7a75 · 28 Oct 2026Report an issue or request a re-scan

• Publishercalesthio GitHub userOwner of the repository this skill is read from
• Source foldercalesthio/openmontage/.agents/skills/elevenlabsThe exact folder we audited
• LicenceAGPL-3.0As the repository states it
• Commit pinned for this verdictcab239da7a75A new audit runs when the source changes
• Repository statusNot archivedLast push 4 days ago
• Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

Its description: Generate AI voiceovers, sound effects, and music using ElevenLabs APIs. Use when creating audio content for videos, podcasts, or games. Triggers include generating voiceovers, narration, dialogue, sound effects from…

---
name: elevenlabs
description: Generate AI voiceovers, sound effects, and music using ElevenLabs APIs. Use when creating audio content for videos, podcasts, or games. Triggers include generating voiceovers, narration, dialogue, sound effects from descriptions, background music, soundtrack generation, voice cloning, or any audio synthesis task.
---

# ElevenLabs Audio Generation

## Current v4 transports

For v4, v4 Turbo, Instant Soundtracks and realtime models, read
[the October integration guide](../provider-refresh-oct23/SKILL.md).
v4 uses Text to Dialogue; Turbo uses the dialogue WebSocket.
Do not send those models to the legacy text-to-speech endpoint.

## OpenMontage provider routing

Inspect the OpenMontage registry before choosing an authentication path.

- Prefer `fal_elevenlabs_tts` when it is available. It provides Eleven v3,
  Multilingual v2, and Turbo v2.5 through the centrally managed fal.ai
  connection; no separate ElevenLabs credential is needed.
- Use `elevenlabs_tts` only when that direct provider is already reported as
  available by the registry.
- In a shared installation, never tell the user to create a `.env`, export a
  key, or paste a credential. Report missing direct-provider access as an
  administrator setup request.

The direct API examples below require a centrally configured
`ELEVENLABS_API_KEY`; they are not the default path when the fal.ai provider is
available.

## Text-to-Speech

```python
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")
```

### Models

| Model | Quality | SSML Support | Notes |
|-------|---------|--------------|-------|
| `eleven_multilingual_v2` | Highest consistency | None | Stable, production-ready, 29 languages |
| `eleven_flash_v2_5` | Good | `<break>`, `<phoneme>` | Fast, supports pause/pronunciation tags |
| `eleven_turbo_v2_5` | Good | `<break>`, `<phoneme>` | Fastest latency |
| `eleven_v3` | Most expressive | None | Alpha — unreliable, needs prompt engineering |

**Choose:** multilingual_v2 for reliability, flash/turbo for SSML control, v3 for maximum expressiveness (expect retakes).

### Voice Settings by Style

| Style | stability | similarity | style | speed |
|-------|-----------|------------|-------|-------|
| Natural/professional | 0.75-0.85 | 0.9 | 0.0-0.1 | 1.0 |
| Conversational | 0.5-0.6 | 0.85 | 0.3-0.4 | 0.9-1.0 |
| Energetic/YouTuber | 0.3-0.5 | 0.75 | 0.5-0.7 | 1.0-1.1 |

### Pauses Between Sections

**With flash/turbo models:** Use SSML break tags inline:
```
...end of section. <break time="1.5s" /> Start of next...
```
Max 3 seconds per break. Excessive breaks can cause speed artifacts.

**With multilingual_v2 / v3:** No SSML support. Options:
- Paragraph breaks (blank lines) — creates ~0.3-0.5s natural pause
- Post-process with ffmpeg: split audio and insert silence

**WARNING:** `...` (ellipsis) is NOT a reliable pause — it can be vocalized as a word/sound. Do not use ellipsis as a pause mechanism.

### Pronunciation Control

**Phonetic spelling (any model):** Write words as you want them pronounced:
- `Janus` → `Jan-us`
- `nginx` → `engine-x`
- Use dashes, capitals, apostrophes to guide pronunciation

**SSML phoneme tags (flash/turbo only):**
```
<phoneme alphabet="ipa" ph="ˈdʒeɪnəs">Janus</phoneme>
```

### Iterative Workflow

1. Generate → listen → identify pronunciation/pacing issues
2. Adjust: phonetic spellings, break tags, voice settings
3. Regenerate. If pauses aren't precise enough, add silence in post with ffmpeg rather than fighting the TTS engine.

## Voice Cloning

### Instant Voice Clone

```python
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}")
```

- Use `client.voices.ivc.create()` (not `client.voices.clone()`)
- Pass file handles in binary mode (`"rb"`), not paths
- Convert m4a first: `ffmpeg -i input.m4a -codec:a libmp3lame -qscale:a 2 output.mp3`
- Multiple samples (2-3 clips) improve accuracy
- Save voice ID for reuse

**Professional Voice Clone:** Requires Creator plan+, 30+ min audio. See [reference.md](reference.md).

## Sound Effects

Max 22 seconds per generation.

```python
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)
```

**Prompt tips:** Be specific — "Heavy footsteps on wooden floorboards, slow and deliberate, with creaking"

## Music Generation

10 seconds to 5 minutes. Use `client.music.compose()` (not `.generate()`).

```python
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)
```

**Prompt structure:** Genre, mood, instruments, tempo, use case. Add "no vocals" or use `force_instrumental=True` for background music.

## Remotion Integration

### Complete Workflow: Script to Synchronized Scene

```
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
```

### Step 1: Generate Per-Scene Audio

Use the toolkit's voiceover tool to generate audio for each scene:

```bash
# Generate voiceover files for each scene

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

git clone https://github.com/calesthio/openmontage
git -C openmontage checkout cab239da7a75

Works in

1. 2026-10-28
   !CAUTION C 79 / 100

   first audit · source cab239da7a75

Questions about elevenlabs

• github.com/calesthio/openmontage/tree/main/.agents/skills/eleven — the audited source at commit cab239da7a75 and every finding aboveObserved · 28 Oct 2026

Spotted something wrong? Report a correction · Methodology