Alla modelleraudioGPT Transcribe

GPT Transcribe

av OpenAI

Testa på Kunya
audio

GPT Transcribe

High-accuracy speech-to-text

Modell-ID:gpt-transcribe

API-dokumentation

Transcribe audio to text.

POST/api/v1/audio/transcriptions
Request body
{
  "model": "gpt-transcribe",
  "file": "(multipart audio file)"
}
cURL-exempel
curl -X POST https://kunya.ai/api/v1/audio/transcriptions \
  -H "Authorization: Bearer kunya_YOUR_API_KEY" \
  -F "[email protected]" \
  -F "model=gpt-transcribe"

Anteckningar

  • •Send audio as multipart form data. Supports mp3, wav, m4a, and webm.
Fullständig API-referensOpenAPI-spec

Priser

Kostnad$0.0078 per minut

Funktioner

Streaming Nej
Vision Nej
Resonemang Nej
Verktyg Nej
LeverantörOpenAI
Testa på Kunya

Liknande modeller

GPT-4o mini TTS

OpenAI

Expressive text-to-speech — steerable tone, emotion, and accent

API-dokumentation

TTS-1 HD

OpenAI

Text-to-speech optimized for quality

API-dokumentation

Google TTS Neural2

Google

Google Neural2 voices — highly natural-sounding TTS using novel synthesis methods

API-dokumentation

Seed Audio 1.0

ByteDance Seed

ByteDance Seed Audio via OpenRouter — natural-language voice casting, 20 preset speakers, voice cloning from reference clips, sound effects in prompts, up to 120s output

API-dokumentation