ElevenLabs
Expressive AI voices and dubbing for video first experiences
ElevenLabs builds advanced AI voice technology that powers text to speech, synthetic narration, and multilingual dubbing at production quality, used in media, games, and creator workflows worldwide. Its platform provides highly expressive voices, cross language voice preservation, and tools for localized dialogue, which makes it ideal for video voiceovers, international versions of content, and character driven storytelling. As a provider within Runware, ElevenLabs complements visual generation by adding voice, narration, and dubbing to image and video pipelines, so teams can ship complete experiences that sound as polished as they look while benefiting from continuous improvements in ElevenLabs research and its growing licensed voice marketplace.
Models by ElevenLabs
Eleven Music v1
Eleven Music v1 is a text to music model for high quality multilingual tracks. Control structure, genre, and style at section level. Generate instrumentals or vocal songs from natural language prompts. Integrate through API for automated soundtrack and content workflows.
Eleven v3
Eleven v3 is a premium text to speech model for production audio. It supports 70+ languages with studio grade quality and precise expressive control using inline audio tags. Ideal for narration, podcasts, dialogue, audiobooks, and game voiceover where stable prosody matters.
Eleven Monolingual v1
Eleven Monolingual v1 is an English only text to speech model from ElevenLabs. It focuses on simple natural delivery and stable output. Ideal for lightweight applications, legacy integrations, or projects that need predictable English voice synthesis with low complexity.
Eleven Flash v2.5
Eleven Flash v2.5 is a real time text to speech model for voice agents and interactive apps. It delivers natural speech in about 75 ms latency across 32 languages. Use it for low latency conversational AI, games, live tools, and large scale TTS workloads.
Eleven Multilingual v2
Eleven Multilingual v2 is a high fidelity multilingual text to speech model for 29 languages. It supports expressive prosody with emotional nuance. Ideal for audiobooks, localization pipelines, customer support and international applications that require natural neural voices.
Eleven Multilingual v1
Eleven Multilingual v1 is an early multilingual text to speech model from ElevenLabs. It converts text to natural speech across major languages. It suits legacy integrations, experimentation, and non critical production flows that do not need the quality of v2.
Eleven Turbo v2
Eleven Turbo v2 is an English text to speech model tuned for low latency and low cost. It generates smooth natural speech for chatbots, IVR flows, and automated announcements. Ideal for production systems that need rapid responses and predictable pricing.
Eleven Flash v2
Eleven Flash v2 is an earlier English speech model that delivers very low latency and clear audio. It is built for live streaming use cases. It also fits real time gaming and interactive tools where rapid voice feedback is critical.
Eleven Turbo v2.5
Eleven Turbo v2.5 delivers fast text to speech for production apps. It targets low latency flows with rich voice quality in 32 languages. Use it to power interactive agents, games, and voice enabled tools that need natural speech with rapid response.