Capabilities
Explore what STT Realtime v5 supports, then use the API section for a request tailored to this model.
Languages
Model Information
- Provider
- Soniox
- Product
- Speech-to-Text
- Release Date
- Jun 16, 2026
- Data Policy
- Not specified
- Region
- US
- Input
- Audio
- Output
- Text
Playground
Try STT Realtime v5 by Soniox. Requests use the selected workspace’s credits and API pricing.
Providers
Compare available endpoints, pricing, and context limits for STT Realtime v5.
| Provider | Context | Output | Input Price | Output Price | Endpoint |
|---|---|---|---|---|---|
| Soniox | Not specified | Text | $0.0017 / minute | — | soniox/stt-rt-v5:soniox |
Prices are catalog rates. Your workspace’s estimate and endpoint pricing determine the final charge.
Input and Output Limits
Formats and limits AudioLab enforces on each request.
| Limit | Value |
|---|---|
| Max bytes | Not specified |
| Max seconds | 3600 |
| Formats | aac, flac, mp3, mpeg, mpga, ogg, opus, wav, webm |
Provider Notes
stt-async-v5 is the upload/create/poll model. stt-rt-v5 supports both AudioLab's uploaded-audio shim and open-ended live WebSocket sessions. Both support language identification, context, diarization, and native one-way or two-way translation; set translate=true together with provider.options.soniox.translation to choose the target behavior.
Performance
Status
Current catalog availability. Your workspace’s access is checked separately before a request runs.
A live availability check is not available right now.
Getting Started
Use your workspace API key and the exact model identifier below. Set the API URL to the endpoint shown in your workspace and keep credentials on your server.
curl "$AUDIOLAB_API_URL/v1/audio/transcriptions" \
-H "Authorization: Bearer $AUDIOLAB_API_KEY" \
-F 'model=soniox/stt-rt-v5' \
-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 | soniox/stt-rt-v5 — Required model identifier. |
client_reference_id | View Accepted Values |
context (general fields, terms, text, translation terms) | View Accepted Values |
enable_language_identification / language_hints / language_hints_strict | View Accepted Values |
translation (one_way or two_way) | View Accepted Values |
webhook_url and webhook auth fields (async) | View Accepted Values |
enable_endpoint_detection / endpoint_latency_adjustment_level | View Accepted Values |
endpoint_sensitivity / max_endpoint_delay_ms (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 | aac, flac, mp3, mpeg, mpga, ogg, opus, wav, webm |
Similar Models
Explore more speech-to-text and compare their capabilities.
| Model | Context | Input Price | Output Price |
|---|---|---|---|
| STT Async v5Soniox | Not specified | $0.0014 / minute | — |
| stt-rt-v4Soniox | Not specified | $0.0017 / minute | — |
| stt-async-v4Soniox | Not specified | $0.0014 / minute | — |
| stt-async-v3Soniox | Not specified | $0.0014 / minute | — |
| stt-rt-v3Soniox | Not specified | $0.0017 / minute | — |
| stt-rt-preview-v2Soniox | Not specified | $0.0017 / minute | — |