Request Parameters
Complete parameter reference for batch transcription endpoints.
Common Parameters
Parameters supported by all batch endpoints:
| Parameter | Type | Required | Description |
|---|---|---|---|
file | file | Yes | Audio file to transcribe (max 25MB) |
model | string | No | Model ID (default: cipher-fast) |
language | string | No | ISO language code (e.g., "en", "hi", "es"). Recommended for best accuracy. |
💡 Best Practice: Always specify the
language parameter when you know the audio language. While auto-detection works well for Cipher models, Lucid models (especially lucid-lite and lucid-agent) perform significantly better with explicit language specification.
Cipher Engine Parameters
Additional parameters for /api/v1/stt/cipher/transcribe:
| Parameter | Type | Default | Description |
|---|---|---|---|
response_format | string | json | Output format: json, text, verbose_json, srt, vtt |
prompt | string | - | Context prompt with domain-specific terms |
timestamp_granularities | string | - | Timestamp detail: word, segment (requires verbose_json) |
Lucid Engine Parameters
Additional parameters for /api/v1/stt/lucid/transcribe:
| Parameter | Type | Default | Description |
|---|---|---|---|
diarize | boolean | false | Enable speaker diarization |
smart_format | boolean | true | Format dates, numbers, currency |
punctuate | boolean | true | Add punctuation |
keywords | string | - | Comma-separated keywords to boost |
Response Format Options
| Format | Description | Content-Type |
|---|---|---|
json | Simple JSON with text and metadata | application/json |
text | Plain text transcription | text/plain |
verbose_json | Detailed JSON with timestamps | application/json |
srt | SubRip subtitle format | text/plain |
vtt | WebVTT subtitle format | text/vtt |
Model Options
| Model | Engine | Credits/sec |
|---|---|---|
cipher-fast | Cipher | 2 |
cipher-max | Cipher | 2 |
lucid-mono | Lucid | 3 |
lucid-multi | Lucid | 3 |
lucid-agent | Lucid | 3 |
lucid-lite | Lucid | 3 |
Example Requests
Basic Request
curl -X POST "https://yourvoic.com/api/v1/stt/transcribe" \
-H "X-API-Key: your_api_key" \
-F "file=@audio.mp3" \
-F "model=cipher-fast"With All Options (Cipher)
curl -X POST "https://yourvoic.com/api/v1/stt/cipher/transcribe" \
-H "X-API-Key: your_api_key" \
-F "file=@audio.mp3" \
-F "model=cipher-max" \
-F "language=en" \
-F "response_format=verbose_json" \
-F "timestamp_granularities=word" \
-F "prompt=Technical terms: API, SDK, microservices"With All Options (Lucid)
curl -X POST "https://yourvoic.com/api/v1/stt/lucid/transcribe" \
-H "X-API-Key: your_api_key" \
-F "file=@meeting.mp3" \
-F "model=lucid-mono" \
-F "language=en" \
-F "diarize=true" \
-F "smart_format=true" \
-F "punctuate=true" \
-F "keywords=YourVoic,API,transcription"