CAPI
Models/Transcription
Audio

Transcription

by OpenAI

Whisper-based speech-to-text with timestamps, diarisation, and translation for long recordings.

Get API KeyRead the docs

Capabilities

  • Speech to text
  • Timestamps
  • Translation

Available models

Pass any of these IDs in the model field.

Model IDDetailPrice
whisper-v3per minute$0.006 / minute
gpt-4o-transcribeper minute$0.010 / minute

Pricing starts at

$0.006 / minute

Pay only for what you use. Each response returns the exact amount settled against your balance — no subscriptions, no minimums.

Quickstart

Transcription · whisper-v3

cURL
curl -X POST https://capi.ai/api/v1/audio/speech \
  -H "Authorization: Bearer YOUR_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"model":"whisper-v3","input":"Welcome to CAPI."}' \
  --output out.mp3

More Audio models

View all
Audio

ElevenLabs

ElevenLabs

ElevenLabs API access for voice synthesis, text-to-speech, sound effects, speech-to-text, and audio isolation.

from $0.040 / 1K charsView
Audio

Fish Audio

Fish Audio

Fish Audio API access for expressive multilingual and production-grade text-to-speech with managed MP3 or WAV output.

from $0.0000 / 1K UTF-8 bytesView
Audio

Gemini TTS

Google

Gemini TTS API access for multi-speaker dialogue with configurable voices, accents, delivery styles, and pacing.

from $0.0014 / 1K tokensView