The ElevenLabs API lets you integrate voice AI into any application — from chatbots to content platforms.

API Quick Start

from elevenlabs import ElevenLabs

client = ElevenLabs(api_key="your-api-key")

audio = client.text_to_speech.convert(
    voice_id="JBFqnCBsd6RMkjVDRZzb",
    text="Hello! Welcome to our platform.",
    model_id="eleven_multilingual_v2"
)

# Save to file
with open("output.mp3", "wb") as f:
    for chunk in audio:
        f.write(chunk)

Streaming for Real-Time Applications

audio_stream = client.text_to_speech.convert_as_stream(
    voice_id="JBFqnCBsd6RMkjVDRZzb",
    text="This streams in real-time for low-latency applications.",
    model_id="eleven_turbo_v2_5"
)

# Stream to audio player or WebSocket
for chunk in audio_stream:
    play_audio(chunk)

Conversational AI

Build voice-enabled AI agents:

1. Define your agent's voice, personality, and knowledge base
2. Configure conversation flow and tools
3. Deploy via WebSocket for real-time voice interaction
4. Users speak naturally and get voice responses

Key API Endpoints

• /text-to-speech — Convert text to speech
• /voice-generation — Design new voices from descriptions
• /dubbing — Submit dubbing jobs programmatically
• /voices — Manage your voice library
• /speech-to-speech — Transform speech with a different voice
• /audio-isolation — Remove background noise from audio

Integration Ideas

• E-learning platforms with AI narration
• Customer service bots with natural voices
• Accessibility tools for visually impaired users
• Content platforms with audio versions of articles
• Gaming NPCs with dynamic dialogue