ElevenLabs

ElevenLabs is a voice AI company founded in 2022 that provides an API for text-to-speech, voice cloning, speech-to-speech conversion, and audio dubbing. Its models produce speech that is consistently ranked as the most natural-sounding available commercially. The API covers 70+ languages with Eleven v3 (29 with Multilingual v2 and 32 with the low-latency Flash and Turbo v2.5 models), with accent-aware output and supports real-time streaming for latency-sensitive applications like conversational AI, interactive assistants, and podcast narration.

Installation

pip install elevenlabs

Basic text-to-speech

from elevenlabs.client import ElevenLabs

client = ElevenLabs(api_key="YOUR_ELEVENLABS_API_KEY")

audio = client.text_to_speech.convert(
    voice_id="JBFqnCBsd6RMkjVDRZzb",  # premade voice: "George"
    model_id="eleven_multilingual_v2",
    text="Willkommen bei ai-solutions.wiki. Hier lernen Sie, wie Sie KI-Systeme in die Praxis umsetzen.",
    output_format="mp3_44100_128",
)

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

Streaming for real-time applications

Use the streaming endpoint (or the WebSocket API for input streamed token by token) when integrating with a conversational agent and need audio to start playing before the full response is generated.

from elevenlabs.client import ElevenLabs
from elevenlabs import stream

client = ElevenLabs(api_key="YOUR_ELEVENLABS_API_KEY")

audio_stream = client.text_to_speech.stream(
    voice_id="JBFqnCBsd6RMkjVDRZzb",
    model_id="eleven_flash_v2_5",  # optimised for low latency
    text="Your order has been confirmed. Delivery is scheduled for Thursday.",
    output_format="pcm_16000",
)

stream(audio_stream)

Voice cloning from a sample

Instant voice cloning accepts audio files of 30 seconds to 5 minutes. The clone is available immediately via the API.

from elevenlabs.client import ElevenLabs

client = ElevenLabs(api_key="YOUR_ELEVENLABS_API_KEY")

cloned_voice = client.voices.ivc.create(
    name="Customer Service Rep - AT",
    description="Austrian German accent, professional tone",
    files=["speaker_sample.mp3"],
)

audio = client.text_to_speech.convert(
    voice_id=cloned_voice.voice_id,
    model_id="eleven_multilingual_v2",
    text="Guten Tag, wie kann ich Ihnen helfen?",
)

Pricing (as of September 2026)

Subscriptions are sold in USD and measured in credits. All ElevenLabs products draw on one shared monthly credit pool; for Multilingual v2, one text character costs one credit, and other models use different rates.

Annual billing charges ten months for twelve, and unused credits roll over for up to two months. For pay-as-you-go API use, ElevenLabs lists text-to-speech at $0.10 per 1K characters for Eleven v3 and Multilingual v2 and $0.05 per 1K for Flash/Turbo and v3 Conversational.

A typical spoken minute of audio is roughly 750-900 characters. 100,000 characters equals approximately 110-130 minutes of audio.

Comparison with alternatives

When not to use ElevenLabs

Very high volume, cost is primary concern: At scale (hundreds of millions of characters per month), Google Cloud TTS or Amazon Polly costs roughly 5-10x less. The quality gap matters less for automated notifications or IVR systems.

Real-time phone telephony at carrier scale: ElevenLabs Agents now supports phone numbers and SIP trunking to connect an existing PBX or SIP provider, so telephony is possible. If you need a full contact-centre platform (routing, queues, compliance recording) rather than a voice agent, Twilio, Vonage or your CCaaS vendor remains the better base, with ElevenLabs as the voice layer.

Purely German or Austrian government output: EU procurement rules may require GDPR-compliant EU-resident processing. Confirm ElevenLabs’ current DPA terms before using voice data from EU citizens.

Accessibility-first static content: For screen readers and ARIA-described content, browser-native Web Speech API or Google TTS with SSML gives you precise phoneme control and no per-character cost.

Further reading

• ElevenLabs API documentation : REST and WebSocket reference, model IDs, voice IDs
• ElevenLabs Python SDK : Full source, examples, changelog
• Voice Library : Premade voices browsable by accent, age, language, use case
• ElevenLabs Agents : Real-time voice agent platform (formerly Conversational AI) with turn detection, interruption handling, phone numbers and SIP trunking
• What is an API? : Foundational explanation of APIs and how to call them
• Multi-Agent Systems : Integrating voice output with agentic workflows

Sources

1. ElevenLabs Python SDK README (models eleven_v3, eleven_multilingual_v2, eleven_flash_v2_5; text_to_speech.stream, voices.ivc.create), checked 26 September 2026. https://github.com/elevenlabs/elevenlabs-python
2. ElevenLabs pricing (subscription plans and credits), checked 26 September 2026. https://elevenlabs.io/pricing
3. ElevenLabs API pricing (per-1K-character rates, language counts per model), checked 26 September 2026. https://elevenlabs.io/pricing/api
4. ElevenLabs docs, “SIP trunking” (ElevenLabs Agents). https://elevenlabs.io/docs/eleven-agents/phone-numbers/sip-trunking