CAPI
Models/Fish Audio
Audio

Fish Audio

by Fish Audio

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

Get API KeyRead the docs

Capabilities

  • Text to speech
  • Voice cloning
  • Multilingual

Available models

Pass any of these IDs in the model field.

Model IDDetailPrice
fish-audio-speech-1.5per 1K bytes$0.015 / 1K UTF-8 bytes

Pricing starts at

$0.0000 / 1K UTF-8 bytes

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

Quickstart

Fish Audio · fish-audio-speech-1.5

cURL
curl -X POST https://capi.ai/api/v1/audio/speech \
  -H "Authorization: Bearer YOUR_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"model":"fish-audio-speech-1.5","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

Gemini TTS

Google

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

from $0.0014 / 1K tokensView
Audio

OpenAI TTS

OpenAI

OpenAI text-to-speech with low-latency streaming voices for real-time assistants.

from $0.015 / 1K charsView