Wizper (Whisper v3)
openai/wizperWizper is a fast Whisper v3 speech-to-text model. It transcribes audio or video in about 100 languages, or translates the speech into English, with segment-level timestamps.
- Base price
- $0.006USD / run
- Execution
- async
- Model type
- audio
- Input fields
- 7
Production route
Try the model
Playground
Input
URL of the audio file to transcribe. Supported formats: mp3, mp4, mpeg, mpga, m4a, wav or webm.
Task to perform on the audio file. Either transcribe or translate. Allowed values: transcribe, translate.
Level of the chunks to return.
1029
Maximum speech segment duration in seconds before splitting. Range: 10 to 29.
Language of the audio file.
If translate is selected as the task, the audio will be translated to
English, regardless of the language selected. If `None` is passed,
the language will be automatically detected. This will also increase
the inference time. Allowed values: af, am, ar, as, az, ba, be, bg, bn, bo, br, bs, ca, cs, cy, da, de, el, en, es, et, eu, fa, fi, fo, fr, gl, gu, ha, haw, he, hi, hr, ht, hu, hy, id, is, it, ja, jw, ka, kk, km, kn, ko, la, lb, ln, lo, lt, lv, mg, mi, mk, ml, mn, mr, ms, mt, my, ne, nl, nn, no, oc, pa, pl, ps, pt, ro, ru, sa, sd, si, sk, sl, sn, so, sq, sr, su, sv, sw, ta, te, tg, th, tk, tl, tr, tt, uk, ur, uz, vi, yi, yo, zh.
Version of the model to use. All of the models are the Whisper large variant.
Whether to merge consecutive chunks. When enabled, chunks are merged if their combined duration does not exceed max_segment_len.
OutputReady
Your output will appear here
Complete the inputs, then click Run.
Model card
Specifications
Pricing
- Base price
- $0.006 / run
Context & modalities
- Input
- Schema-defined
- Output
- audio
Capabilities
- Chat
- Not supported
- Vision
- Not supported
- Reasoning
- Not supported
- Structured output
- Not supported
- Function calling
- Not supported
- Audio input
- Not supported
Access
- Provider
- OpenAI
- Model ID
- openai/wizper
- Execution
- async
- Base URL
- https://api.sandbase.ai
- API
- Unified Run API
- Endpoint
- /v1/run
API README
Wizper (Whisper v3)
Wizper is a fast Whisper v3 speech-to-text model: transcribe audio in about 100 languages, or translate it to English.
Fields
| Field | Type | Default | Notes |
|---|---|---|---|
audio | audio URL | — | Audio or video URL to transcribe. |
task | transcribe / translate | transcribe | transcribe keeps the source language; translate outputs English. |
chunk_level | string | segment | Timestamp granularity. |
max_segment_len | integer 10–29 | 29 | Maximum segment length in seconds. |
language | af / am / ar / as / az / ba / be / bg / bn / bo / br / bs / ca / cs / cy / da / de / el / en / es / et / eu / fa / fi / fo / fr / gl / gu / ha / haw / he / hi / hr / ht / hu / hy / id / is / it / ja / jw / ka / kk / km / kn / ko / la / lb / ln / lo / lt / lv / mg / mi / mk / ml / mn / mr / ms / mt / my / ne / nl / nn / no / oc / pa / pl / ps / pt / ro / ru / sa / sd / si / sk / sl / sn / so / sq / sr / su / sv / sw / ta / te / tg / th / tk / tl / tr / tt / uk / ur / uz / vi / yi / yo / zh | en | Source language code. |
version | string | 3 | Version of the model to use. |
merge_chunks | boolean | true | Merge short segments. |
Billing
$0.006 per request, whatever the audio length.
| Request | Price |
|---|---|
| One file | $0.006 |
Failed runs are not charged.
Limits
- One audio file per request.
Start building
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/run" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "openai/wizper",
"task": "transcribe",
"audio": "https://static.sandbase.ai/examples/elevenlabs/scribe-v2/input_audio_0.mp3",
"version": "3",
"language": "en",
"chunk_level": "segment",
"merge_chunks": true,
"max_segment_len": 29
}
SANDBASE_JSON
)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
status=$(printf '%s' "$result" | jq -r .status)
case "$status" in completed|failed|timeout) break ;; esac
sleep 2
result=$(curl --fail-with-body --silent \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
"https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"Choose your model
Compare models
| Model | Type | Default price | Released |
|---|---|---|---|
Wizper (Whisper v3)This model OpenAI | Audio | $0.01 / run | Apr 8, 2024 |
OpenAI | llm | — | Oct 26, 2026 |
OpenAI | llm | — | Oct 26, 2026 |
OpenAI | llm | — | Sep 29, 2026 |
OpenAI | llm | — | Sep 29, 2026 |
OpenAI | llm | — | Sep 22, 2026 |
Questions
FAQ
How do I call OpenAI Wizper (Whisper v3) through SandBase?
Create a SandBase API key, then send requests with the model ID "openai/wizper" to Unified Run API (/v1/run) at https://api.sandbase.ai. The request examples on this page show the exact payload.
Do I need a separate OpenAI account?
No. One SandBase API key and balance gives you access to OpenAI Wizper (Whisper v3) and the other models in the catalog; you do not need to sign up with OpenAI separately.