Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Yandex / SpeechKit

SpeechKit LiveTTS

SpeechKit LiveTTS: text-to-speech model documented in Yandex AI Studio.

Speech & voice
availableClosed weightsText-to-speech
Official documentation (opens in a new tab)Reviewed 14 Oct 2026
8 of 20 specification fields collected
Text input limitAPI v3: 250 normally; 5,000 in unsafe/streaming mode.See specification notes below
Languages1 listedFull language list in specifications
Input billingNot collectedYandex SpeechKit
Output billingNot collectedNo inferred price

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 input tokens
Not collected
Maximum output
Not collected
Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected
Streaming
SupportedSource for Streaming (opens in a new tab)
Batch processing
Not collected
Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
Not collected
Parameters
Not collected
Languages
RussianSource for Languages (opens in a new tab)
Context caching
Not collected
Input modalities
TextSource for Input modalities (opens in a new tab)
Output modalities
AudioSource for Output modalities (opens in a new tab)
Native model options
livettsSource for Native model options (opens in a new tab)
Stock voice catalog
6 LiveTTS voicesSource for Stock voice catalog (opens in a new tab)
Voice controls
Role selection; no speed, pitch_shift, duration, templates, MAX_PEAK or word timings in UtteranceSynthesis. Streaming also omits speed, pitch_shift and MAX_PEAK.Source for Voice controls (opens in a new tab)
Maximum prompt characters
API v3: 250 normally; 5,000 in unsafe/streaming mode.Source for Maximum prompt characters (opens in a new tab)

General service limits; Realtime has a separate contract. Normal API v3 also has a 24-second output limit.

Access & pricing

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

Yandex SpeechKit

Provider source (opens in a new tab)
API model ID
livetts
Access
Authenticated provider API; account access and quotas apply.
Regions
Contract and deployment dependent; exact processing location not verified.

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

Data & enterprise terms

Model-specific retention and training-use terms not collected.

Yandex SpeechKit

Provider source (opens in a new tab)
API model ID
gpt://<folder_ID>/speech-realtime-tts-live/latest
Access
Speech TTS Live: synthesis only, no LLM and no audio input.
Regions
Contract and deployment dependent; exact processing location not verified.

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

Data & enterprise terms

Model-specific retention and training-use terms not collected.

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.

Yandex SpeechKit

livetts
Not verified

No current exact-endpoint cache policy verified.

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.

Caching reviewed 14 Oct 2026

Yandex SpeechKit

gpt://<folder_ID>/speech-realtime-tts-live/latest
Not verified

No current exact-endpoint cache policy verified.

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.

Caching reviewed 14 Oct 2026

Voice choices

6 voices

Choose a voice within SpeechKit LiveTTS. These are API voice identifiers, not additional model releases. Source links document each voice.

Published voice catalog
Voice / API IDLanguage & accentDelivery
Sofiasofiaru-RU
Not separately documented		SpeechKit LiveTTS voice. Roles: casual, support. API v3 and compatible LiveTTS Realtime models.Voice source (opens in a new tab)
Veraveraru-RU
Not separately documented		SpeechKit LiveTTS voice. Roles: casual, support. API v3 and compatible LiveTTS Realtime models.Voice source (opens in a new tab)
Vasilyvasilyru-RU
Not separately documented		SpeechKit LiveTTS voice. Roles: support, sales. API v3 and compatible LiveTTS Realtime models.Voice source (opens in a new tab)
Sergeysergeyru-RU
Not separately documented		SpeechKit LiveTTS voice. Roles: support, sales. API v3 and compatible LiveTTS Realtime models.Voice source (opens in a new tab)
Denisdenisru-RU
Not separately documented		SpeechKit LiveTTS voice. Roles: casual, formal, neutral, sales. API v3 and compatible LiveTTS Realtime models.Voice source (opens in a new tab)
Irinairinaru-RU
Not separately documented		SpeechKit LiveTTS voice. Roles: formal, support, narrator, sales, neutral. API v3 and compatible LiveTTS Realtime models.Voice source (opens in a new tab)

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

Native provider model documented through hosted APIs. No exact matching weight release was found in the reviewed official Yandex model inventory. Public Lite 5, Alice Foundation and Alice T5 checkpoints are excluded, and are not assumed equivalent to the hosted model.

Classification evidence (opens in a new tab)

Sources reviewed