Skip to content
Model infoModelsSnapshot: 15 Oct 2026

ElevenLabs / Speech synthesis

Eleven Multilingual v2

Speech synthesis from text, with model-specific language and delivery controls.

Speech & voice
availableClosed weightsText-to-speech
Official documentation (opens in a new tab)Reviewed 12 Oct 2026
5 of 18 specification fields collected
Text input limit10,000 characters per requestSee specification notes below
Languagesen, ja, zh, de, hi, fr, ko, pt, it, es, id, nl, tr, fil, pl, sv, bg, ro, ar, cs, el, fi, hr, ms, sk, da, ta, uk, ruSee specification notes below
Input billingSee ratesElevenLabs API
Output billingSee ratesPublished units and conditions below

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
Not collected
Maximum output
Not collected
Input modalities
TextSource for Input modalities (opens in a new tab)
Output modalities
SpeechSource for Output modalities (opens in a new tab)
Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected
Streaming
Not collected
Batch processing
Not collected
Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
Not collected
Parameters
Not collected
Architecture
Not collected
Languages
en, ja, zh, de, hi, fr, ko, pt, it, es, id, nl, tr, fil, pl, sv, bg, ro, ar, cs, el, fi, hr, ms, sk, da, ta, uk, ruSource for Languages (opens in a new tab)
Maximum prompt characters
10,000 characters per requestSource for Maximum prompt characters (opens in a new tab)
Supported API routes
/v1/text-to-speech/{voice_id}Source for Supported API routes (opens in a new tab)
Context caching
Not collected

See endpoint caching records. No verified support claim for this model.

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

ElevenLabs API

Provider source (opens in a new tab)
API model ID
eleven_multilingual_v2
Access
API key and eligible account required. Route: /v1/text-to-speech/{voice_id}.
Regions
Default service uses US data storage. Enterprise EU, India and Singapore residency environments are separate workspaces; storage location alone does not guarantee in-region processing.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Speech synthesis · standardUsage1$0.081K characters

Rate conditions

  1. API USD pricing, observed October 12, 2026. Excludes taxes. Published API unit rate. Plan allowances and voice-specific modifiers should be checked separately.
Pricing source (opens in a new tab)

Data & enterprise terms

Zero Retention Mode is restricted to eligible Enterprise API requests and must be enabled. Web UI traffic is excluded; review the documented scope and exceptions.

Read the service policy (opens in a new tab)

Descript editor

Provider source (opens in a new tab)
API model ID
Not collected

Descript UI label: Multilingual v2. No confirmed native provider API selector or pinned backend checkpoint is exposed by this source.

Access
Choose this model in Descript App Settings → AI models or the applicable generation tool. Availability depends on the plan; exact native provider checkpoint IDs are not exposed.
Regions
Managed service; exact model-processing region not verified
Native model options
Multilingual v2Source for Native model options (opens in a new tab)

Application selection label. This access record does not assert that Descript exposes every upstream provider API feature or pins an exact snapshot.

Billing basis
Uses Descript AI credits from a shared plan allowance; exact cost depends on selected model, media length and operation. Provider-native token/character tariffs do not apply to this host.Source for Billing basis (opens in a new tab)
Shared credit bundles
Creator/Business top ups: 350 credits/$35, 1,000/$80, 4,000/$200; valid 12 months and used after included monthly creditsSource for Shared credit bundles (opens in a new tab)

Bundle prices are shared across tools, not a fixed generation price.

Languages
View all 19 entries
  • English (US)
  • Finnish
  • Portuguese (Portugal)
  • Slovak
  • Croatian
  • French (FR)
  • Romanian
  • Turkish
  • Czech
  • German
  • Malay
  • Danish
  • Hungarian
  • Polish
  • Spanish (US)
  • Dutch
  • Italian
  • Portuguese (Brazil)
  • Swedish
Source for Languages (opens in a new tab)

Descript lists 19 app-supported locales. Upstream model language coverage may be wider.

Voice cloning
Authorized custom voice clones and compatible ElevenLabs Voice Library voicesSource for Voice cloning (opens in a new tab)

Recorded consent statement required; existing clones cannot receive more training samples. Community stock voices can disappear at their owners’ discretion.

Generation controls
No tone-tag control for Multilingual v2Source for Generation controls (opens in a new tab)

Raw square-bracket tone prompts are blocked in the current Descript v3/v4 workflow. This is different from native-provider prompt conventions.

Output formats
Generated speech in the project; convert to a standard audio layer for timeline fades or Studio SoundSource for Output formats (opens in a new tab)

Endpoint pricing has not been collected. Check the provider for applicable rates.

Data & enterprise terms

Descript help states that production models use no Descript user data; internal research/development uses data only from users who opted in. Enterprise data sharing is disabled by default. Partner agreements prohibit using submitted data to train partner AI. This is not a blanket zero-retention promise; project storage and deletion have separate policies.

Read the service policy (opens in a new tab)

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

ElevenLabs API

eleven_multilingual_v2
Not verified

Provider-side caching has not been verified for this endpoint. Missing documentation is not evidence that caching is unsupported.

How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
Not collected

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Descript editor

Not verified

No model-specific discounted prompt-cache contract collected. Project reuse, stored voices and persistent editing conversations do not establish caching.

How it works
Not collected

No model-specific discounted prompt-cache contract collected. Project reuse, stored voices and persistent editing conversations do not establish caching.

Minimum reusable input
Not collected

No model-specific discounted prompt-cache contract collected. Project reuse, stored voices and persistent editing conversations do not establish caching.

Lifetime & refresh
Not collected

No model-specific discounted prompt-cache contract collected. Project reuse, stored voices and persistent editing conversations do not establish caching.

How to enable it
Not collected

No model-specific discounted prompt-cache contract collected. Project reuse, stored voices and persistent editing conversations do not establish caching.

Usage fields
Not collected

No model-specific discounted prompt-cache contract collected. Project reuse, stored voices and persistent editing conversations do not establish caching.

Billing rules
Not collected

No model-specific discounted prompt-cache contract collected. Project reuse, stored voices and persistent editing conversations do not establish caching.

Limits & data boundaries
Not collected

No model-specific discounted prompt-cache contract collected. Project reuse, stored voices and persistent editing conversations do not establish caching.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

ElevenLabs-developed managed model. Reviewed release documentation supplies service access and no downloadable weights; proprietary speech, transcription and turn-taking families are explicitly described by the provider.

Classification evidence (opens in a new tab)

Sources reviewed