Yandex SpeechKit
Yandex Cloud's managed Russian-first STT + TTS with batch and streaming.
Yandex Cloud's managed Russian-first STT + TTS with batch and streaming.
Best for russian-language workloads, Russia-region tenants, voice assistants in the CIS market. Pricing: tiered per-second (RUB-denominated).
What it is
Yandex SpeechKit is Yandex Cloud's speech platform, providing streaming and batch ASR plus neural TTS. It is the dominant managed service for Russian-language transcription with strong coverage of Russian and several CIS languages, plus English and Turkish in select models. Features include speaker diarization, word-level timestamps, profanity filtering, and custom language model boosting. Pricing is denominated in rubles with tiered per-second rates. Best fit: russian-language workloads, russia-region tenants, voice assistants in the cis market. Caveats: sanctions exposure: international card payment + signup availability has been restricted at various points; verify access before relying on it. Pricing as listed: tiered per-second (RUB-denominated). Feature flags from vendor docs: speaker diarization, word-level timestamps, streaming. Directory tags: commercial-api, hyperscaler, regional-cis. Last vendor-page check: 2026-05-12.
Watch out for: Sanctions exposure: international card payment + signup availability has been restricted at various points; verify access before relying on it.
Install / use
Yandex SpeechKit gRPC: yandexcloud.ai.stt.v3.RecognizerFeatures
| Speaker diarization | Yes |
| Word-level timestamps | Yes |
| Streaming / real-time | Yes |
| Languages supported | None |
| HIPAA eligible | No |
Yandex SpeechKit vs Whipscribe
| Feature | Yandex SpeechKit | Whipscribe |
|---|---|---|
| Category | Transcription APIs | Transcription APIs |
| Pricing | tiered per-second (RUB-denominated) | free beta |
| Speaker diarization | Yes | Yes |
| Word timestamps | Yes | Yes |
| Streaming | Yes | No |
| Languages | — | 99 |
| Platforms | API | Web, API, MCP |
Alternatives to Yandex SpeechKit
Whipscribe is a managed faster-whisper + whisperX service. If you want transcripts without running infrastructure, paste a URL or drop a file in the form below — you'll have a transcript in seconds.