Fish Audio TTS
Fish Audio TTS is a multilingual text-to-speech model from Fish Audio, tuned for natural prosody, voice cloning from short reference samples, and broad language coverage. It supports streaming generation for real-time applications and is competitive with leading open-ecosystem TTS systems. Use it for assistants, dubbing, and production voice pipelines that need cloning support.
Pricing
Input
$15.00 / 1M chars
Output
—
Pay only for what you use. No subscriptions, no minimums.
Specs
- Context
- —
- Max output
- —
- Latency
- Fast
- Category
- Audio
Constraints & limits
Max input
Per provider
Output
MP3 (32 kHz, 128 kbps, mono)
The gateway auto-clamps requests to the model's limits where possible.
Quick start
This sample hits the text-to-speech endpoint. Change base_url and your key, then run it.
from openai import OpenAI
client = OpenAI(
api_key="tl-xxxxxxxxxxxxxxxxxxxxxxxx",
base_url="https://api.thalam.ai/v1",
)
response = client.audio.speech.create(
model="fish-audio/fish-tts",
input="Welcome to Thalam, your unified gateway to AI models.",
)
with open("out.mp3", "wb") as f:
f.write(response.content)Similar models
ElevenLabs v3
ElevenLabs v3: gold-standard voice synthesis.
ElevenLabs Multilingual v2
ElevenLabs Multilingual v2: faithful, consistent voice synthesis.