ElevenLabs TTS

The ElevenLabs TTS provider enables your agent to use ElevenLabs' high-quality text-to-speech models for generating natural, expressive voice output with advanced voice cloning capabilities.

Installation

Install the ElevenLabs-enabled VideoSDK Agents package:

pip install "videosdk-plugins-elevenlabs"

Importing

from videosdk.plugins.elevenlabs import ElevenLabsTTS, VoiceSettings

Authentication

The ElevenLabs plugin requires an ElevenLabs API key.

Set ELEVENLABS_API_KEY in your .env file.

Example Usage

from videosdk.plugins.elevenlabs import ElevenLabsTTS, VoiceSettings
from videosdk.agents import CascadingPipeline

# Configure voice settings
voice_settings = VoiceSettings(
    stability=0.71,
    similarity_boost=0.5,
    style=0.0,
    use_speaker_boost=True
)

# Initialize the ElevenLabs TTS model
tts = ElevenLabsTTS(
    # When ELEVENLABS_API_KEY is set in .env - DON'T pass api_key parameter
    api_key="your-elevenlabs-api-key",
    model="eleven_flash_v2_5",
    voice="EXAVITQu4vr4xnSDxMaL",
    speed=1.0,
    response_format="pcm_24000",
    enable_streaming=True,
    enable_ssml_parsing=False,
    apply_text_normalization="auto",
    auto_mode="auto",
    voice_settings=voice_settings,
)

# Add tts to cascading pipeline
pipeline = CascadingPipeline(tts=tts)

note

When using .env file for credentials, don't pass them as arguments to model instances or context objects. The SDK automatically reads environment variables, so omit api_key, videosdk_auth, and other credential parameters from your code.

Configuration Options

• model: The ElevenLabs model to use (e.g., "eleven_flash_v2_5", "eleven_multilingual_v2")
• voice: (str) Voice ID to use for audio output (default: "EXAVITQu4vr4xnSDxMaL")
• speed: (float) Speed of the generated audio (default: 1.0)
• api_key: Your ElevenLabs API key (can also be set via environment variable)
• response_format: (str) Audio format for output (default: "pcm_24000")
• voice_settings: (VoiceSettings) Advanced voice configuration options:
  • stability: (float) Voice stability (0.0 to 1.0, default: 0.71)
  • similarity_boost: (float) Voice similarity enhancement (0.0 to 1.0, default: 0.5)
  • style: (float) Voice style exaggeration (0.0 to 1.0, default: 0.0)
  • use_speaker_boost: (bool) Enable speaker boost for clarity (default: True)
• base_url: (str) Custom base URL for ElevenLabs API (optional)
• enable_streaming: (bool) Enable real-time audio streaming (default: False)
• enable_ssml_parsing: (bool) Whether to enable SSML parsing (default: False)
• apply_text_normalization: (str) Controls text normalization (e.g., spelling out numbers). Modes:
  • "auto" (default) – System decides automatically
  • "on" – Always applied
  • "off" – Skipped
  • Note: For eleven_turbo_v2_5 and eleven_flash_v2_5 models, enabling text normalization requires an Enterprise plan.
• auto_mode: (bool) Reduces latency by disabling chunk schedule and buffers. Recommended for full sentences/phrases.

Additional Resources

The following resources provide more information about using ElevenLabs with VideoSDK Agents SDK.

• ElevenLabs docs: ElevenLabs TTS docs.

SDK Reference

GitHub Repository

Python Package