S1

fish-audio/s1

A text-to-speech model, at $15.75 per million characters.

Details

Maker: fish-audio
Kind: Speech
Price: $15.75 per million characters
Capabilities: None listed
Takes: Text
Returns: Audio
Zero data retention: Not on every provider
No training on requests: Not on every provider
Released: 2025-10-20
Newer model: fish-audio/drama-3Released later by the same maker, costs no more, and lists the same capabilities. Compare the two

Description

Fish Audio S1 is trained on over 2 million hours of audio with online RLHF (GRPO). It achieves 0.8% WER and 0.4% CER on Seed TTS Eval. S1 supports open-domain emotion, tone, and special effect markers.

Call it

curl

curl https://phantom.codes/v1/audio/speech \
  -H "Authorization: Bearer $PHANTOM_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "fish-audio/s1",
    "input": "Hello from Phantom"
  }' \
  --output speech.mp3

Set PHANTOM_KEY to your key. Any OpenAI client works with the base URL https://phantom.codes/v1.

Get a key Compare with another model