MODELS / FISH AUDIO

Transcribe-1

Turn spoken audio into accurate text — with timed segments — using Fish Audio’s ASR model. Send an audio file, get back the transcript, its duration, and timestamped segments.

TRANSCRIPTION
—
CONTEXT WINDOW
—
MAX OUTPUT TOKENS
<$0.001 / 1M tokens
INPUT PRICE
—
OUTPUT PRICE
QUICKSTART

Call it in one request.

OpenAI-compatible — change the base URL, and the setup is complete.

SHELL
curl https://enterprise.blackbox.ai/v1/chat/completions \
  -H "Authorization: Bearer $BLACKBOX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "blackboxai/fish-audio/transcribe-1",
    "messages": [{ "role": "user", "content": "Hello!" }],
    "stream": true
  }'
INPUT: audioOUTPUT: textRELEASED: 2026-03-01
RELATED MODELS

Also worth a look.

FISH AUDIO

S1

— context · $15 / 1M tokens input · — output

FISH AUDIO

S2 Pro

— context · $15 / 1M tokens input · — output

FISH AUDIO

S2.1 Pro

— context · $15 / 1M tokens input · — output