ElevenLabs#

ElevenLabs provides one of the highest-quality text-to-speech engines available. JSON2Video integrates with ElevenLabs out of the box so you can add realistic voiceovers to videos with a single element.

You can use ElevenLabs in two modes:

• Through JSON2Video (default): credits come from your JSON2Video balance. No ElevenLabs account required.
• Bring your own key: connect your ElevenLabs account and pay ElevenLabs directly. Useful for high-volume use cases or for accessing custom cloned voices.

Basic usage#

Add a voice element with model: "elevenlabs":

{
  "type": "voice",
  "model": "elevenlabs",
  "voice": "Adam",
  "text": "Hello, I am an ElevenLabs generated voiceover."
}

Browse available voices at json2video.com/ai-voices/elevenlabs. The voice field accepts either a voice name ("Adam", "Rachel") or an ElevenLabs voice ID.

The Flash v2.5 model#

For shorter latency at the same quality tier, use elevenlabs-flash-v2-5:

{
  "type": "voice",
  "model": "elevenlabs-flash-v2-5",
  "voice": "Adam",
  "text": "This is a Flash v2.5 voiceover."
}

Credit consumption is the same as the standard ElevenLabs model.

Bring your own ElevenLabs API key#

If you have an ElevenLabs subscription with custom voices or need higher rate limits, connect your account:

Step 1 — Get an ElevenLabs API key#

1. Sign in at elevenlabs.io.
2. Open your profile menu → API Keys.
3. Create a new key and copy it.

Step 2 — Create a JSON2Video Connection#

1. Go to json2video.com/dashboard/connections.
2. Click Add new connection.
3. Choose ElevenLabs as the type.
4. Paste the API key.
5. Give the connection an ID you'll remember (e.g. my-elevenlabs) and save.

Step 3 — Reference the connection in your movie JSON#

{
  "type": "voice",
  "model": "elevenlabs",
  "connection": "my-elevenlabs",
  "voice": "p16ZaTyG1Ks9FQ9LpSun",
  "text": "Hello, world!"
}

When connection is set, JSON2Video calls ElevenLabs with your API key. You pay ElevenLabs for the generation; JSON2Video charges a small handling fee for the orchestration. See the credits reference for current rates.

Picking a voice#

ElevenLabs offers two voice categories:

• Pre-built voices — available to everyone. Names like Adam, Rachel, Domi, Bella, Antoni, …
• Cloned / custom voices — created in your ElevenLabs account and only accessible with your own API key (via a Connection).

Browse pre-built voices at json2video.com/ai-voices/elevenlabs — each card includes a playable sample. For custom voices, find the voice ID in your ElevenLabs dashboard.

Customising voice settings#

Pass any ElevenLabs API parameter through model-settings:

{
  "type": "voice",
  "model": "elevenlabs",
  "voice": "Adam",
  "text": "Hello, world!",
  "model-settings": {
    "language_code": "en",
    "voice_settings": {
      "stability": 0.75,
      "similarity_boost": 0.85,
      "style": 0.2,
      "speed": 1.0
    }
  }
}

Common parameters:

• voice_settings.speed — playback speed, 0.7 to 1.2 (default 1.0).
• voice_settings.stability — 0.0 to 1.0. Higher = more consistent but less expressive.
• voice_settings.similarity_boost — 0.0 to 1.0. Higher = closer to the source voice.
• voice_settings.style — 0.0 to 1.0. Higher = more emotional / dramatic.
• language_code — ISO 639-1 code (en, es, fr, …) to force a specific language.

See ElevenLabs API docs for the full list.

Cost#

Without a Connection, ElevenLabs usage consumes credits from your JSON2Video balance — see the credit consumption table.

With a Connection, you pay ElevenLabs directly for the audio generation and JSON2Video charges a much smaller orchestration fee per voice element.

See also#

• Voice element reference
• Dashboard — Connections
• Tutorial 7 — AI voiceover
• Credits & limits