Context-aware expressive speech
The model interprets speaker context, preceding events, and intended delivery to produce more expressive narration and dialogue.
Eleven v4
Eleven v4 and Eleven v4 Turbo are expressive AI text-to-speech models for narration, dialogue, multilingual voice content, and real-time voice agents. They help creators and developers control emotion, speaker context, pauses, and audio events, with Turbo optimized for streaming conversations.
Expressive text-to-speech for narration and live conversations
Eleven v4 and Eleven v4 Turbo are ElevenLabs text-to-speech models for generating expressive spoken audio from written scripts. V4 is positioned for emotive narration and dialogue, while v4 Turbo uses the same expressive range in a model designed for real-time interactions and voice agents.
The models support speaker-aware delivery, emotional direction, audio events, and multi-speaker scenes. Eleven v4 is available in ElevenLabs apps, and v4 Turbo is available through the API and ElevenAgents; the wider ElevenLabs platform also provides voice selection, voice cloning, Studio workflows, dubbing, and other creative audio tools, with availability varying by plan and product surface.
Key features
Script-level direction and audio events
Add tags such as [laughs], [whispers], pauses, and sound cues like [door slams] directly to the script to direct performance and scene details.
Multilingual multi-speaker generation
Generate multi-speaker scenes with emotional variation, conversational delivery, and built-in sound effects across more than 90 languages.
Long-form continuity
Context stitching is designed to maintain pacing and delivery across long scripts, helping long-form output sound continuous rather than segmented.
Speaker stability during regeneration
Regenerate individual lines while maintaining the same speaker identity across dialogue and narration, reducing vocal drift between takes.
Real-time Turbo streaming
Eleven v4 Turbo supports bidirectional streaming, with median time to first speech of about 150 ms and median inference latency of about 100 ms, according to the product page.
Use cases
Audiobooks and narrative production
Create audiobooks, serialized stories, and dramatic scripts with multiple characters, pauses, emotional direction, and sound cues while using context stitching for consistent long-form delivery.
Podcasts, courses, and explainers
Produce podcasts, explainers, and educational material with conversational or instructional voices, multilingual versions, and controlled pacing.
Real-time voice agents
Build customer-service, sales, and support agents that stream generated speech as an LLM produces text, allowing responses, confirmations, escalations, and holds to receive different delivery.
Multilingual localization
Generate localized voice content for audiences in different markets, using multilingual speech and Professional Voice Clones where the cloned voice supports the target language.
Video, games, and branded content
Create branded voiceovers and character performances for video, social content, games, and advertising using the broader ElevenLabs voice library and voice tools.
Pros and Cons
Pros
- Supports expressive direction through script tags, pauses, emotions, and sound events.
- Handles multi-speaker and long-form speech workflows with context stitching and speaker stability.
- Offers speech in more than 90 languages and supports Professional Voice Clones in v4.
- Turbo is designed for streaming, agent loops, and live conversational response times.
- Can be used across app, API, and agent workflows, depending on the model.
Cons
- The available evidence does not specify a complete model-by-model plan matrix, output limits, or all API setup requirements.
- Some capabilities, including voice cloning, Studio, dubbing, and collaboration, are part of the broader ElevenLabs platform and may depend on the selected product or subscription tier.
FAQ
Where can Eleven v4 and Eleven v4 Turbo be used?
Eleven v4 is available through ElevenLabs web and mobile apps, while Eleven v4 Turbo is available through the API and ElevenAgents for real-time speech workflows.
How do you control expression and sound in Eleven v4?
Eleven v4 accepts direction in the script, including tags such as [laughs], [whispers], and [door slams]. It can also handle multi-speaker dialogue, emotional delivery, pauses, and built-in sound effects.
What is Eleven v4 Turbo designed for?
Eleven v4 Turbo is designed for live interactions. Text can be streamed in as an LLM generates it, with audio streamed back before the sentence is complete through bidirectional streaming.
Which languages and voice-cloning options are supported?
Eleven v4 supports speech in more than 90 languages. Turbo is specifically described as speaking Japanese, Spanish, and Portuguese text with native accents, while both models support Professional Voice Clones across the languages those voices speak.
How is ElevenLabs Text to Speech usage billed?
ElevenLabs uses shared credits across its products. Text to Speech is listed at approximately 1 credit per character, although the exact cost can vary by model and API pricing rules; plans include a free tier and paid tiers.
Quick Facts
- Category
- AI text-to-speech
- Models
- Eleven v4 and Eleven v4 Turbo
- Primary workflows
- Narration, dialogue, voice agents, and real-time conversations
- Language coverage
- More than 90 languages for Eleven v4
- Turbo access
- API and ElevenAgents
- Platform
- ElevenLabs web and mobile apps, API, and agent products
Alternatives à Eleven v4
Fylom
Fylom is an AI podcast generator that turns a topic or question into a researched narrated episode. It supports typed or spoken prompts, voice selection, and recurring show-style listening.
Gemini 3.8 Text-to-Speech
Gemini 3.8 Text-to-Speech is Google’s pair of expressive audio models for turning scripts into customizable spoken audio. Creators, developers and enterprises can design voices, direct delivery line by line, and generate dialogue for content, dubbing and voice-agent applications.
Kugel 3.5
Kugel 3.5 is KugelAudio’s text-to-speech model for voice agents and phone conversations, with controls for short replies, IPA pronunciation, timed pauses and character-by-character codes. It retains Kugel 3’s documented voices, languages, dictionaries and API while charging €0.0525 per audio minute excluding VAT, billed per second.
Gemini 3.1 Flash TTS
Gemini 3.1 Flash TTS is Google’s preview text-to-speech model for generating expressive AI speech with fine-grained control over style and delivery. It is available across the Gemini API, Google AI Studio, Vertex AI, and Google Vids.
蓝藻AI
蓝藻AI是一款在线AI配音与语音合成产品，可将文字转成语音，并支持自助声音克隆。页面信息显示它面向短视频、有声书等需要配音的内容场景。
Ondoku
Ondoku 是一款基于浏览器的文字转语音软件，可将文本转换为可下载的 .mp3 语音，并提供免费额度与付费方案。它支持多语言朗读、图片朗读以及按规则商用。