genshiai-stt 4.0.0

GENSHI Works STT SDK — high-accuracy domain-specific speech-to-text

GENSHI Works STT SDK

High-accuracy domain-specific speech-to-text SDK. Supports batch transcription and realtime streaming with built-in VAD and on-device STT inference.

Installation

Python

pip install genshiai-stt

Node.js

npm install @genshiai/stt

The correct native addon for your platform is installed automatically via optional dependencies.

Browser

npm install @genshiai/stt-web

Quick Start

Python

import asyncio

from genshi_stt import GenshiSTTClient

async def main() -> None:
    async with GenshiSTTClient(api_key="gw-...") as client:
        with open("recording.wav", "rb") as f:
            result = await client.transcribe(f.read())
        print(result.text)
        for seg in result.segments:
            print(f"[{seg.start:.2f}-{seg.end:.2f}] {seg.text}")

        async with client.stream(
            domain="medical",
            secure=True,
            effort="normal",
            dictionary_ids=["dict_hospital"],
            dictionaries=[
                {
                    "id": "dict_hospital",
                    "name": "院内用語",
                    "industry": "medical",
                    "terms": [{"term": "GENSHI AI", "reading": "げんしえーあい"}],
                }
            ],
        ) as session:
            partials = await session.push(audio_chunk)  # PCM16 bytes
            print(partials[0].text if partials else "")

            refined = await session.drain_events()
            for event in refined:
                if event.type == "refined":
                    print(event.index, event.text)

            final = await session.finalize()
            print(final.text)

asyncio.run(main())

Node.js / TypeScript

import { GenshiSTTClient } from '@genshiai/stt';

const client = new GenshiSTTClient({ apiKey: 'gw-...' });

// Batch transcription
const result = await client.transcribe(audioBuffer);
console.log(result.text);
for (const seg of result.segments) {
  console.log(`[${seg.start.toFixed(2)}-${seg.end.toFixed(2)}] ${seg.text}`);
}

// Realtime streaming
const session = client.stream({
  domain: 'medical',
  secure: true,
  effort: 'normal',
  dictionaryIds: ['dict_hospital'],
  dictionaries: [
    {
      id: 'dict_hospital',
      name: '院内用語',
      industry: 'medical',
      terms: [{ term: 'GENSHI AI', reading: 'げんしえーあい' }],
    },
  ],
});
const partials = await session.push(pcm16Chunk);
console.log(partials[0]?.text);

const refined = await session.drainEvents();
for (const event of refined) {
  if (event.type === 'refined') {
    console.log(event.index, event.text);
  }
}

const final = await session.finalize();
console.log(final.text);

Browser

import { GenshiSTTClient, createMicStream } from '@genshiai/stt-web';

const client = new GenshiSTTClient({ apiKey: 'gw-...' });
await client.init();

const session = client.stream({
  domain: 'medical',
  secure: true,
  effort: 'normal',
  dictionaryIds: ['dict_hospital'],
  dictionaries: [
    {
      id: 'dict_hospital',
      name: '院内用語',
      industry: 'medical',
      terms: [{ term: 'GENSHI AI', reading: 'げんしえーあい' }],
    },
  ],
});

const mic = await createMicStream({
  onChunk: async (chunk) => {
    const partials = await session.push(chunk);
    console.log(partials[0]?.text);

    const refined = await session.drainEvents();
    for (const event of refined) {
      if (event.type === 'refined') {
        console.log(event.index, event.text);
      }
    }
  },
});

// When done:
mic.stop();
const result = await session.finalize();
console.log(result.text);

Prefer await session.finalize() when you need the final corrected text. await session.close() now performs a best-effort finalize for cleanup. Use session.abort() only for intentional force-abort without billing finalize.

Choosing A Mode

Mode	During recording	Correction cadence	Recommended for
batch	Nothing is emitted until the request finishes	One final full-text pass	File upload, post-processing
realtime + effort="normal"	partial text appears immediately	Background correction is sparse	Dictation, meeting notes, standard live input
realtime + effort="high"	partial text appears immediately	Background correction is more frequent	Live captions, simultaneous charting, terminology-sensitive input

Realtime Mental Model

• push() returns immediate partial events from local STT
• drain_events() / drainEvents() returns queued refined / error events from background correction
• effort: "normal" batches corrections sparsely, effort: "high" refines more often
• finalize() still performs the final full-text correction pass

secure=True / secure: true requests the Secure tier. Secure requests require an industry domain such as medical, or inline custom dictionaries. Public SDK configuration is intentionally centered on domain, secure, dictionaryIds / dictionaries, and effort. Low-level VAD and local model tuning are not part of the public API.

Realtime Event Example

push() returns a partial event:

{
  "type": "partial",
  "text": "ほんじつのけつあつは130の80です。",
  "index": 0,
  "processing_time_ms": 0
}

drain_events() / drainEvents() returns a refined event for the same segment:

{
  "type": "refined",
  "text": "本日の血圧は130の80です。",
  "index": 0,
  "processing_time_ms": 88
}

Response

{
  "text": "本日の血圧は130の80です。次の患者さんをお願いします。",
  "processing_time_ms": 142,
  "segments": [
    {
      "id": 0,
      "start": 0.32,
      "end": 2.15,
      "text": "本日の血圧は130の80です。"
    },
    {
      "id": 1,
      "start": 3.2,
      "end": 4.8,
      "text": "次の患者さんをお願いします。"
    }
  ]
}

Pricing

Point-based billing. 1pt = ¥10. Billed per audio hour at finalize().

Standard

Domain	Batch	Realtime (normal)	Realtime (high)
General	2 pt/h (¥20)	5 pt/h (¥50)	7 pt/h (¥70)
Industry-specific	4 pt/h (¥40)	6 pt/h (¥60)	8 pt/h (¥80)
+ Custom Dictionary	6 pt/h (¥60)	7 pt/h (¥70)	10 pt/h (¥100)

Secure

Secure tier processes audio within a private VPC. Requires secure: true and a domain such as medical, or custom dictionaries.

Domain	Batch	Realtime (normal)	Realtime (high)
General	7 pt/h (¥70)	8 pt/h (¥80)	10 pt/h (¥100)
Industry-specific	8 pt/h (¥80)	10 pt/h (¥100)	12 pt/h (¥120)
+ Custom Dictionary	9 pt/h (¥90)	10 pt/h (¥100)	13 pt/h (¥130)

Effort levels:

• effort: "normal" — background correction every 30-60s. Recommended for dictation, meeting notes, standard realtime input.
• effort: "high" — more frequent correction (every 15-30s). Recommended for live captions, simultaneous charting, terminology-sensitive input.

Final correction (finalize()) is always included regardless of effort level.

See https://docs.genshi.ai/stt/pricing for details.

Supported Platforms

Platform	Python	Node.js
macOS ARM64 (Apple Silicon)	genshiai-stt-native	@genshiai/stt-native-darwin-arm64
Linux x64	genshiai-stt-native	@genshiai/stt-native-linux-x64
Windows x64	genshiai-stt-native	@genshiai/stt-native-windows-x64
Browser	—	@genshiai/stt-web

Requirements

• Python >= 3.10 / Node.js >= 20
• Valid GENSHI Works API key
• ffmpeg for Python file/bytes decode and Node.js encoded audio decode

Browser SDK note:

• await client.init() is required before transcribe() or realtime()
• the npm package includes JSON metadata, and secured ONNX assets are fetched via POST /v1/activate

Documentation

Full documentation: https://docs.genshi.ai/stt

License

Proprietary. Copyright (c) 2026 GENSHI Works Inc. All rights reserved. See LICENSE.