Free
$0per month10,000 credits per month (roughly 10 minutes of v4 audio) for personal use; includes Text to Speech, Speech to Text, Sound Effects and Voice Design. Official source 1 ↗ · Official source 2 ↗
Reviewed tool profile
Eleven v4
ElevenLabs’ most expressive text-to-speech model, with a low-latency Turbo variant for voice agents.
Sources checked
- Pricing
- In the ElevenLabs apps, Eleven v4 uses the same credit pricing as other text-to-speech models (1 credit per character) and is available on every plan, including the Free plan with 10,000 credits a month. Paid plans run from Starter at $6/month to Business at $990/month. Through the API it is billed in USD per 1,000 characters: $0.08 for v4 and $0.04 for v4 Turbo, shown at 72% off ($0.022 and $0.011) until October 12. Official source 1 ↗ · Official source 2 ↗ · Official source 3 ↗
- Available as
- Available in the ElevenLabs web and mobile apps (Web, iOS and Android). · Available through the ElevenLabs API via REST, streaming endpoints and TypeScript and Python SDKs; Eleven v4 Turbo is also available in ElevenAgents for voice agents. Official source 1 ↗ · Official source 2 ↗ Official source 1 ↗
- Primary group
- Voice & Speech
What it does
Eleven v4 is ElevenLabs’ newest text-to-speech model family, released in October 2026 in two variants. Eleven v4 is tuned for produced content such as narration and audiobooks, with a new architecture, a wider emotional range, multiple speakers and inline sound effects. Eleven v4 Turbo is a low-latency variant (about 100 ms median inference) for voice agents and real-time use. Both support 90+ languages and Professional Voice Clones.
Official source 1 ↗Features
- Expressive, actor-like delivery. A new architecture reads a script like a voice actor, with a wide emotional range, multiple speakers and built-in sound effects. Official source 1 ↗
- Inline audio tags. Direction such as [laughs], [whispers] or [door slams] goes straight into the script, and v4 follows tag sequences more reliably than v3. Official source 1 ↗
- Long-form consistency. Context stitching keeps pacing steady across long scripts, and the speaker stays the same across regenerations. A single generation supports up to 10,000 characters. Official source 1 ↗
- Voice cloning and voice library. Professional Voice Clones return after being unavailable in v3; every clone requires verified consent. All 17,500+ library voices work with v4. Official source 1 ↗
- Eleven v4 Turbo for real time. About 100 ms median inference latency and about 150 ms time to first speech, with bidirectional streaming for agent loops. Official source 1 ↗
- 90+ languages. Both variants support more than 90 languages. Official source 1 ↗
- Standard output formats. Outputs MP3, WAV/PCM and µ-law for telephony, with sample rate and bitrate set through the API. Official source 1 ↗
Pricing & free limits
Starter
$6per month ($1 first month until Oct 18)30,000 credits per month, commercial licence and Instant Voice Cloning. Official source 1 ↗
Creator
$22per month ($11 first month)121,000 credits per month and Professional Voice Cloning. Official source 1 ↗
Pro
$99per month600,000 credits per month, 44.1kHz PCM output via API and 192kbps audio. Official source 1 ↗
Scale
$299per month1,800,000 credits per month, 3 workspace seats and 3 Professional Voice Clones. Official source 1 ↗
Business
$990per month6,000,000 credits per month, 10 seats, 10 Professional Voice Clones and low-latency TTS from 5c/minute. Official source 1 ↗
Enterprise
Custom pricingcontact salesCustom terms, DPA/SLAs, HIPAA BAAs, custom SSO and more seats and voices. Official source 1 ↗
API — Eleven v4
$0.08 per 1K characters ($0.022 at 72% off until Oct 12)pay as you go, USDPay-as-you-go API pricing for the quality-focused model. Official source 1 ↗
API — Eleven v4 Turbo
$0.04 per 1K characters ($0.011 at 72% off until Oct 12)pay as you go, USDPay-as-you-go API pricing for the low-latency model. Official source 1 ↗
Billing details
Launch offer: on Creator plans and above, up to 2x monthly TTS credits used on v4 do not count against the balance for two weeks, in the web and mobile apps only. Official source 1 ↗
Annual billing charges 10 months for a year. Unused paid-plan credits roll over for up to two months; rollover does not apply to the Free plan. Official source 1 ↗
Free access & limits
The Free plan includes 10,000 credits a month, roughly 10 minutes of Eleven v4 audio. Official source 1 ↗
Best for & limitations
Narrate audiobooks and long scripts with consistent pacing and voice. Official source 1 ↗
Produce multi-speaker dialogue with emotion and sound effects for podcasts, games or animation. Official source 1 ↗
Power real-time voice agents and phone calls with Eleven v4 Turbo. Official source 1 ↗
Create branded voices with Professional Voice Clones that stay consistent across languages. Official source 1 ↗
Localise audio into 90+ languages. Official source 1 ↗
- SSML breaks disabled. SSML tags such as <break> do not work in v4; pauses and emphasis must use natural-language audio tags. Official source 1 ↗
- Older clones need retraining. Instant and Professional Voice Clones made before v4 must be retrained to work well with it. Official source 1 ↗
- Per-generation length cap. One generation is limited to 10,000 characters; longer work relies on context stitching. Official source 1 ↗
- Launch prices are temporary. The 72% API discount runs only until October 12, and the 2x credit offer only for two weeks in the apps. Official source 1 ↗ · Official source 2 ↗
Similar tools
Tools like Eleven v4
Published tools that share its categories.
MusicfyAI voice song generator for making covers in other voices, training a clone of your own voice, and generating music from text prompts.
Visit 
AlituBrowser-based podcast maker that records calls, cleans up audio automatically, edits by transcript or waveform, and hosts and publishes episodes.
Visit 
Kits AIAI vocal and audio tools for music producers: custom voice cloning, royalty-free AI singing voices, stem splitting, vocal cleanup, harmonies and AI mastering.
Visit 
CastmagicAI content platform that turns podcast episodes and other recordings into transcripts, show notes, clips, newsletters and social posts.
Visit 
RiversideBrowser-based studio that records podcasts and video in separate local tracks, with a text-based editor and AI cleanup, clips and show notes.
Visit 
Cleanvoice AIAI podcast editor that removes filler words, silences, mouth sounds and background noise from audio and video, with timeline export and an API.
Visit