Fish Transcribe-1

Speech price
First audio: median latency
Completion: median duration

01RoutesLoading

02Capabilities

Input: audio
Output: text
Context: —
Max output: —

Audio input

03Quick start

Call it with your RProuter key

Any OpenAI-compatible SDK works. Point it at the RProuter base URL from your API keys page and use this model ID.

Quick start guide Create an API key

Catalog source: docs.fish.audio · checked 2026-09-09

POST /v1/audio/speech
Authorization: Bearer YOUR_RPROUTER_KEY

{
  "model": "fish/transcribe-1",
  "voice": "YOUR_RPROUTER_VOICE_ID",
  "input": "Every story starts somewhere.",
  "response_format": "mp3"
}