The Stack · Voice, speech & video API

ElevenLabs

Ultra-realistic text-to-speech, voice cloning, dubbing, and voice-agent APIs for developers and creators.

API keyFreemium🔵 agent: self serve instant keyMCP ✓

Get API key → instant key, usually no card Docs Website

CategoryVoice, speech & video

TypeAPI service

Authapi-key

PricingFreemium

Agent signup🔵 self serve instant key

SDKsPython, TypeScript, REST

MCP serveravailable →

Pricing: Free tier 10k credits/mo; TTS ~$0.10/1k chars (Multilingual v2), Flash ~$0.05; PAYG available (prices cut mid-2026).

🔵 Agents: self serve instant key

Instant self-serve — free signup gives a key immediately (a human unblocks an agent in under 2 minutes).

Free email signup, no credit card; API key issued instantly under Settings → API Keys. No public account-provisioning API.

ElevenLabs — Ultra-realistic text-to-speech, voice cloning, dubbing, and voice-agent APIs for developers and creators.
Website: https://elevenlabs.io
Docs: https://elevenlabs.io/docs
Get a key: https://elevenlabs.io/sign-up
Agent signup: self serve instant key — Free email signup, no credit card; API key issued instantly under Settings → API Keys. No public account-provisioning API.
Auth: api-key
MCP server: https://github.com/elevenlabs/elevenlabs-mcp
Pricing: freemium — Free tier 10k credits/mo; TTS ~$0.10/1k chars (Multilingual v2), Flash ~$0.05; PAYG available (prices cut mid-2026).
Full record: https://dreaming.press/api/tools/elevenlabs.json

Machine record: /api/tools/elevenlabs.json · add its MCP server →

Quickstart

from elevenlabs import ElevenLabs, play

client = ElevenLabs(api_key="ELEVENLABS_API_KEY")
audio = client.text_to_speech.convert(
    voice_id="JBFqnCBsd6RMkjVDRZzb",
    model_id="eleven_multilingual_v2",
    text="The first move is what sets everything in motion.",
    output_format="mp3_44100_128",
)
play(audio)

python · full docs →

Model Context Protocol

ElevenLabs exposes an MCP server, so you can add its tools to Claude, Cursor, or any MCP client: https://github.com/elevenlabs/elevenlabs-mcp

ElevenLabs in our coverage

Full-Duplex Voice Is the Headline. Cascaded Is Still the Product: Choosing a Voice Stack After GPT-Live

2026-07-11

Generative Media Just Hit Commodity Pricing: Images at $0.034 a Thousand, Editable Video at ~$1 a Clip — and the Voice Catch

2026-07-11

The Model Got Cheap the Same Week the Money Got More Concentrated

2026-07-10

Higgs Audio v3: A Chat-Native Open TTS for Voice Agents — With a License You Have to Read

2026-07-05

Cartesia vs ElevenLabs vs Kokoro: Choosing TTS for Voice Agents

2026-06-22

Speech-to-Speech vs Cascaded: Two Architectures for Voice AI Agents in 2026

2026-06-22

ElevenLabs FAQ

What is ElevenLabs?

ElevenLabs is Ultra-realistic text-to-speech, voice cloning, dubbing, and voice-agent APIs for developers and creators. It's in the Voice, speech & video category of the dreaming.press tool directory.

Is ElevenLabs free?

ElevenLabs is freemium — free to start, paid plans for scale. Free tier 10k credits/mo; TTS ~$0.10/1k chars (Multilingual v2), Flash ~$0.05; PAYG available (prices cut mid-2026)..

Can an AI agent sign up for ElevenLabs automatically?

Almost — signup is instant and self-serve (a free key with no sales call), so a human can unblock an agent in under two minutes. Free email signup, no credit card; API key issued instantly under Settings → API Keys. No public account-provisioning API..

Does ElevenLabs have an MCP server?

Yes — ElevenLabs offers a Model Context Protocol server, so you can add its tools to Claude, Cursor, or any MCP client: https://github.com/elevenlabs/elevenlabs-mcp

Is ElevenLabs open source?

ElevenLabs is a hosted API service, not an open-source project.

What languages does ElevenLabs support?

ElevenLabs offers Python, TypeScript, REST.