What is Whisper Tiny API?
Whisper: Multilingual speech recognition model, robust, versatile, open-source.
Technical Specifications
- Supported inputs: Audio
- Output: Text
Performance Benchmarks
[embed]
Whisper Tiny API Pricing
- Pricing on request
Where to Use Whisper Tiny
Transcription
Convert calls, meetings, and media into accurate, searchable text.
Captioning and indexing
Generate subtitles and make audio archives searchable.
Whisper Tiny is a speech-to-text model that takes audio as input and produces text output. It is used for audio transcription, including converting spoken content into written text.
It can be used for captioning and subtitles, where audio from videos, meetings, or live recordings is turned into readable text. It also fits voice-note or voicemail transcription workflows that need speech converted into text for later reading or search.
Because it is a speech-to-text model, it can support call-center or interview transcription pipelines that store spoken audio as text records. It can also be used to create text transcripts for archive, review, or accessibility purposes.
import requests, time headers = {"Authorization": "Bearer " + AIMLAPI_KEY} job = requests.post( "https://api.aimlapi.com/v1/stt/create", headers=headers, json={ "model": "deepgram/whisper-tiny", "url": "https://example.com/audio.mp3" }, ).json() gid = job["generation_id"] while True: res = requests.get(f"https://api.aimlapi.com/v1/stt/{gid}", headers=headers).json() if res.get("status") in ("completed", "error", "failed"): break time.sleep(3) print(res)
const headers = { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }; const job = await (await fetch("https://api.aimlapi.com/v1/stt/create", { method: "POST", headers, body: JSON.stringify({ "model": "deepgram/whisper-tiny", "url": "https://example.com/audio.mp3" }), })).json(); let res; do { await new Promise((r) => setTimeout(r, 3000)); res = await (await fetch(`https://api.aimlapi.com/v1/stt/${job.generation_id}`, { headers })).json(); } while (!["completed", "error", "failed"].includes(res.status)); console.log(res);
# submit the job — the response contains "generation_id" curl -X POST https://api.aimlapi.com/v1/stt/create \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"deepgram/whisper-tiny","url":"https://example.com/audio.mp3"}' # then poll for the result until it is ready curl "https://api.aimlapi.com/v1/stt/{generation_id}" -H "Authorization: Bearer $AIMLAPI_KEY"
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Output | |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Whisper Tiny This page | Transcription | |||
| Speech synthesis | ||||
| Speech synthesis | ||||
| Speech synthesis | ||||
| Speech synthesis |
Whisper Tiny takes audio as input and returns text.
Whisper Tiny became available on December 30, 2025.
Whisper Tiny is priced at output $0.0000715 / sec.
Whisper Tiny was built by Deepgram.
Use deepgram/whisper-tiny as the model id on AI/ML API.
Yes. Whisper Tiny is served through AI/ML API, so the same key and endpoint format used for other models applies.
Yes, Whisper Tiny is offered by Deepgram under the model id deepgram/whisper-tiny for speech-to-text.
Whisper Tiny is described as a multilingual speech recognition model, but no specific language list is provided.
Yes, Deepgram describes Whisper Tiny as an open-source multilingual speech recognition model.
