whisper
unofficialstt
whisper specifications
| Context window | — |
|---|---|
| Max output tokens | — |
| Release date | — |
| Input | Audio |
| Output | Text |
whisper pricing in rubles
You pay for what you use, per token and per unit. The final request cost is returned in the API response.
| Type | Price |
|---|---|
| Transcription | 0,065 ₽ per minute |
Prices are in rubles and may change with exchange rates.
What whisper can do
- Streaming responses
whisper API: connection and code examples
The service exposes a single OpenAI-compatible API. Set our base_url and the key from your dashboard.
cURL
curl https://api.neuralbridge.ru/v1/audio/transcriptions \
-H "Authorization: Bearer YOUR_API_KEY" \
-F model="openai/whisper-08130" \
-F file=@record.mp3API endpoints
POST /v1/audio/transcriptionsprimary | Audio — transcriptions Transcribe a recording, with timecodes and speaker separation where the model supports it. |
Supported request parameters
| Parameter | Default | Allowed values | Description |
|---|---|---|---|
language | — | — | Language of the material: a hint about which language is spoken or written. Usually speeds up and sharpens processing. |
response_format | json | — | Response format: plain text or strict JSON following a given schema. |
temperature | — | — | Controls how varied the answer is: higher values make the output more random, lower values more predictable. |