TTS · STT · Realtime · Intelligence

Voice kit API – speech synthesis & recognition API

A cloud API for speech: neural synthesis and voice cloning, audio-to-text transcription, and real-time analysis – from a single request to live streaming sessions.

Get an API key Listen to the demo Open documentation

Solutions

Voice AI for your workflow

Four ready-made products on one API — from speech synthesis to call quality control.

Call quality control

Score every call against a checklist, with evidence and alerts.

Learn more →

Meeting protocols

TL;DR, decisions and tasks from a meeting recording.

Learn more →

Recording library and search

Tags, folders, PDF export and semantic search.

Learn more →

Voice verification

Voice biometrics and spoof protection.

Learn more →

About the platform

Speech synthesis and recognition API

Voice kit API – a cloud platform for speech: neural text-to-speech and voice cloning, timestamped transcription, real-time streaming transcription and VAD turn detection, diarization, intelligence analysis (emotions, topics, summaries, PII redaction), and Voice ID – a voice passport with 1:1 verification and 1:N identification. It suits narration, voice assistants, call centers, interviews, and meetings.

Integration takes minutes: sign up, get an API key, and send HTTP or WebSocket requests. Synthesis returns audio in MP3, WAV, or OGG; transcription and analysis return structured JSON; streaming returns live events. The platform is optimized for Russian and detects the recording language automatically.

Voices with emotions and cloning, TTS and STT streaming, VAD detection, Voice ID verification and identification, long-form synthesis for audiobooks, audio and video effects, webhooks for async jobs, official SDKs, and transparent pricing – from a free plan to enterprise limits.

Features

What the platform can do

Synthesis, recognition, and an intelligence layer over audio – in one API.

Voice generation

Speech synthesis

29 voices, emotions, speed, and pitch. MP3, WAV, OGG, and chunk streaming for long texts.

Voice cloning

Your own voice from one recording: 3–30 seconds of clean speech and synthesis in 9 languages.

Long-form synthesis

Turn articles and books into speech: async synthesis with a sample-accurate WAV and a timed paragraph manifest.

Speech understanding

Transcription

Audio to text with word-level timestamps, keyterm prompting, and automatic language detection. Up to 15 minutes.

Text intelligence

Topics, summaries, PII redaction, language detection, and automatic keywords – no audio upload required.

Semantic search & Q&A

Search by meaning and ask questions over your recordings (RAG) with verbatim citations and timestamps.

Voice intelligence & audio

Voice ID New

Voice passport – language, gender, age and emotion – plus 1:1 verification and 1:N identification by speaker fingerprint.

Speakers & emotions

Diarization splits a recording into speakers; sentiment shows the mood by segment – joy, anger, neutral.

Audio post-production

A chain of 7 effects (reverb, EQ, compressor, pitch) plus one-click noise removal and loudness normalization.

Batch

Bulk synthesis and analysis in one request, processed in the background.

Webhooks

Notifications when async jobs are ready.

OpenAPI

Full Swagger spec for client generation.

Who it's for

Who Voice kit API is for

From call centers to product teams – the platform covers any team working with Russian speech.

Call centers

Transcribe calls, separate speakers, and analyze emotions – for QA and agent coaching.

Content & EdTech

Voice over articles, courses, and videos with natural voices, including cloning your branded voice.

Developers

REST and WebSocket, Python/JS/.NET SDKs, webhooks, and OpenAPI – integrate in 15 minutes.

Product teams

Add voice features to your product – assistants, subtitles, call analytics – without an in-house ML team.

Demo

Try the platform without a key

Speech synthesis – up to 500 characters, audio-to-text transcription – up to 30 seconds. No sign-up.

No-code

An API without programming

The dashboard includes a playground: synthesis, transcription, and analysis right in the browser – not a single line of code. Requests count toward your account usage.

Open the playground

Integrations

Close the loop: from a recording to the CRM deal

The transcript, the meeting protocol and the call QA report land straight in a Bitrix24, amoCRM or 1C deal. Connect once — everything else is automatic.

Bitrix24, amoCRM, 1C

One connection layer for every system: a Bitrix24 incoming webhook, an amoCRM token or a 1C HTTP service. Secrets stay encrypted and repeated pushes are idempotent.

A protocol you can file

Decisions, tasks with owners, risks and next steps in one protocol. Export to DOCX or PDF, share a public link or push it to the CRM with one click.

Events for automation

The meeting.completed and qa.violation webhooks let you wire the finished result into anything: notifications, tasks, reporting, reminders.

Recording → transcription and diarization → protocol or QA score → CRM deal. No manual file forwarding.

Connect in the cabinet Compare plans

Plans

Pricing

Start free. Top up your balance with crypto and pay for any plan in your dashboard.

Free

Free / month

  • 5,000 synthesis characters
  • 150 audio minutes
  • No diarization
  • No cloning
  • —
  • —
  • No streaming
  • Audio effects
  • Standard queue
Start free

Basic

390 ₽ / month

  • 500,000 synthesis characters
  • 1800 audio minutes
  • Diarization
  • Voice cloning — up to 5 voices
  • —
  • —
  • No streaming
  • Audio effects
  • Standard queue
Pay

Pro

1490 ₽ / month

  • 2,000,000 synthesis characters
  • 9000 audio minutes
  • 200,000 LLM tokens
  • Diarization
  • Voice cloning — up to 50 voices
  • Call QA
  • CRM integrations
  • Chunk streaming
  • Audio effects
  • Standard queue
Pay

Business

7990 ₽ / month

  • 7,000,000 synthesis characters
  • 30000 audio minutes
  • 1,000,000 LLM tokens
  • Diarization
  • Voice cloning — up to 500 voices
  • Call QA
  • CRM integrations
  • Chunk streaming
  • Audio effects
  • Priority queue
Temporarily unavailable

Some plans are temporarily unavailable while we scale up capacity – they'll be back soon.

A simple scheme: synthesis characters, audio minutes (recognition, analysis, effects) and LLM tokens for generative features. Beyond the limit — per-minute overage from your balance.

All plans and pricing
We accept
  • СБП
  • МИР
  • Visa
  • Mastercard
  • Cryptocurrency

Integration

Two calls – the whole platform

Key in X-Api-Key. Synthesis returns binary audio; transcription, VAD, and analysis return JSON.

Speech synthesis

POST /v1/synthesize

One POST – a ready audio file.

Show request example 
POST /v1/synthesize
X-Api-Key: rtt_…
Content-Type: application/json

{
  "text": "Добрый день. Это синтез русской речи.",
  "voice": "preset_anna",
  "format": "mp3"
}

Transcription

POST /v1/transcribe

Async job with a webhook: get job_id and fetch the result.

Show request example 
POST /v1/transcribe
X-Api-Key: rtt_…
Content-Type: multipart/form-data

audio=meeting.mp3
language=ru
diarization=true

→ 202 { "job_id": "…" }

GET /v1/transcribe/{job_id}
→ { "transcript": "…", "segments": […] }

VAD / turn detection

POST /v1/vad

Upload audio and get speech segments back.

Show request example 
POST /v1/vad
X-Api-Key: rtt_…
Content-Type: multipart/form-data

audio=call.mp3

→ {
  "segments": [{ "start": 1.2, "end": 4.8 }],
  "speech_ratio": 0.42,
  "duration_seconds": 8.6,
  "processing_time_ms": 123
}

Audio analysis

POST /v1/analyze

Transcription plus emotions, keywords, entities, and speakers.

Show request example 
POST /v1/analyze
X-Api-Key: rtt_…
Content-Type: multipart/form-data

audio=call.mp3
language=ru

→ {
  "transcript": "…",
  "segments": […],
  "keywords": […],
  "entities": […],
  "speakers": […]
}

Long-form synthesis

POST /v1/synthesize/async

Async synthesis for long texts with a timed paragraph manifest.

Show request example 
POST /v1/synthesize/async
X-Api-Key: rtt_…
Content-Type: application/json

{
  "text": "Глава 1. …\n\nГлава 2. …",
  "voice": "preset_anna"
}

→ 202 { "job_id": "…" }

GET /v1/synthesize/async/{job_id}
→ { "paragraphs": [{ "start": 0.0, "end": 12.4 }] }

GET /v1/synthesize/async/{job_id}/audio
→ WAV · sample-accurate

Audio effects

POST /v1/audio/effects

A chain of effects for audio and video – an async job with a webhook.

Show request example 
POST /v1/audio/effects
X-Api-Key: rtt_…
Content-Type: multipart/form-data

audio=voice.wav
effects=[{"type":"reverb"},{"type":"eq","bands":[…] }]
output_format=mp3

→ 202 { "job_id": "…" }

GET /v1/audio/effects/{job_id}/audio
→ processed audio
Open documentation

Platform

One API for every speech workflow

Blog

From the blog

Tutorials and deep dives on speech recognition, synthesis, diarization, and voice cloning.

All articles

FAQ

Frequently asked questions

What is Voice kit API?

It's a REST platform combining speech synthesis, transcription, and audio analysis. You send a request with an API key and get a ready audio file or structured JSON.

Which languages and formats are supported?

Synthesis is optimized for Russian; transcription detects the recording language automatically. Audio is returned in MP3, WAV, and OGG.

How do I get an API key?

Sign up in the dashboard – the key is created automatically. Send it in the X-Api-Key header on every request.

Is there a free plan?

Yes, the Free plan includes 5,000 synthesis characters and 150 audio minutes per month (recognition, analysis, effects) – no card required.

How do I pay for a plan?

Pay for any plan in your dashboard – we accept SBP bank transfers and bank cards, as well as crypto (USDT, BTC, ETH). The subscription renews automatically.

Is there real-time streaming and voice cloning?

Voice cloning in 9 languages is available on Basic (up to 5 voices), Pro (up to 50), and Business (up to 500) via POST /v1/voices/clone. Streaming transcription and VAD over WebSocket are available on Pro and Business.