Capabilities
Explore what Pulse supports, then use the API section for a request tailored to this model.
Languages
Model Information
- Provider
- Smallest.ai
- Product
- Speech-to-Text
- Data Policy
- Not specified
- Region
- Global
- Input
- Audio
- Output
- Text
Playground
Try Pulse by Smallest.ai. Requests use the selected workspace’s credits and API pricing.
Providers
Compare available endpoints, pricing, and context limits for Pulse.
| Provider | Context | Output | Input Price | Output Price | Endpoint |
|---|---|---|---|---|---|
| Smallest.ai | Not specified | Text | $0.0026 / minute | — | smallest/pulse:smallest |
Prices are catalog rates. Your workspace’s estimate and endpoint pricing determine the final charge.
Input and Output Limits
Formats and limits AudioLab enforces on each request.
| Limit | Value |
|---|---|
| Max bytes | Not specified |
| Max seconds | 3600 |
| Formats | flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, webm |
Provider Notes
Pulse supports batch and realtime multilingual recognition; the available language host is region-dependent. Pulse Pro is batch-only and English-only, and does not label speakers, so AudioLab rejects diarize for it. AudioLab's live route sends mono PCM16, so realtime encoding is fixed to linear16 even though the uploaded-audio API documents additional encodings. The catalog uses Pulse's realtime price ceiling while one-shot usage is charged at its lower batch price.
Performance
Status
Current catalog availability. Your workspace’s access is checked separately before a request runs.
A live availability check is not available right now.
Getting Started
Use your workspace API key and the exact model identifier below. Set the API URL to the endpoint shown in your workspace and keep credentials on your server.
curl "$AUDIOLAB_API_URL/v1/audio/transcriptions" \
-H "Authorization: Bearer $AUDIOLAB_API_KEY" \
-F 'model=smallest/pulse' \
-F 'file=@recording.wav'Request Parameters
Available parameters depend on the provider and request format. The endpoint reference explains accepted values and required fields.
| Parameter | Details |
|---|---|
model | smallest/pulse — Required model identifier. |
word_timestamps / sentence_timestamps | View Accepted Values |
diarize / redact_pii / redact_pci | View Accepted Values |
emotion_detection / gender_detection | View Accepted Values |
keywords / format / itn_normalize / profanity_filter | View Accepted Values |
punctuate / capitalize / encoding | View Accepted Values |
max_words / eou_timeout_ms / finalize_on_words (realtime) | View Accepted Values |
Input and Output Limits
Formats and limits AudioLab enforces on each request.
| Limit | Value |
|---|---|
| Max bytes | Not specified |
| Max seconds | 3600 |
| Formats | flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, webm |
Similar Models
Explore more speech-to-text and compare their capabilities.
| Model | Context | Input Price | Output Price |
|---|---|---|---|
| Pulse ProSmallest.ai | Not specified | $0.0034 / minute | — |
| MAI-Transcribe 2Microsoft Azure | Not specified | $0.0014 / minute | — |
| Gemini 3.5 TranscribeGoogle Gemini | Not specified | $0.0043 / minute | — |
| Saaras v4Sarvam AI | Not specified | ₹0.425 / minute | — |
| saaras-v4-batchSarvam AI | Not specified | ₹0.425 / minute | — |
| qwen-audio-3.0-asr-flashAlibaba Cloud Model Studio | Not specified | $0.0018 / minute | — |
