Fish Audio S2.1-Pro

fish-audio/s2.1-pro

Fish Audio S2.1-Pro API pricing

Fish Audio S2.1-Pro costs $0.006 per 1K characters on Oxyy. That is the pay-as-you-go price after the current 60% discount (Launch Promo; standard price $0.015). It takes text and audio as input and returns audio, from audio files of up to 50 MB. A cheaper Fish Audio option is Fish Audio S2.1-Pro Free, which is free to call; for every model and rate, see Fish Audio API pricing.

Fish Audio's recommended production TTS model and an improved version of S2-Pro, with natural-language bracket control and multi-speaker dialogue.
ModalitiesTextAudioAudio
Price$0.006 per 1K charactersAll Fish Audio API pricing

Providers

Where this model runs, and what each route costs. Requests are sent to a healthy provider automatically; if one errors, the gateway retries against another serving the same model.

ProviderPriceUnit
Fish Audio$0.006per 1K characters

Capabilities (8)

StreamingVoice CloningMulti SpeakerEmotion ControlPronunciation DictionariesPhoneme ControlOpen WeightsProduction Sla

Supported parameters (21)

modeltextreference_idreferencestemperaturetop_pprosodychunk_lengthmin_chunk_lengthnormalizeformatsample_ratemp3_bitrateopus_bitratelatencymax_new_tokensrepetition_penaltycondition_on_previous_chunksearly_stop_thresholdfeaturespronunciation_dictionary

Any other parameter you send is ignored rather than rejected.

Pricing

What this model costs on Oxyy, pay as you go. "Charged" is the rate a request is billed at; the standard price is shown beside it for reference.

Price
$0.006
per 1K characters · standard price $0.015
Current discount
60%
off every rate
RateStandard priceChargedUnit
Per 1K characters$0.015$0.006per 1K characters

Discount. Charged rates include the current "Launch Promo" discount of 60% on every rate.

Specifications

Model ID
s2.1-pro
Developer
Fish Audio
Type
Text to speech
Input
Text and audio
Output
Audio
Audio input
Up to 50 MB each · WAV, MPEG, FLAC
Endpoint
/v1/audio/speech

Best for

Text to speechVoice cloningEmotion control

Quickstart

Call s2.1-pro with a POST to /v1/audio/speech on https://api.oxyy.ai, using your Oxyy API key from the OXYY_API_KEY environment variable. The same key works for every model in the catalog.

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.oxyy.ai/v1",
    api_key=os.environ["OXYY_API_KEY"],
)

with client.audio.speech.with_streaming_response.create(
    model="s2.1-pro",
    voice="alloy",
    input="Hello from Oxyy.",
    response_format="mp3",
) as response:
    response.stream_to_file("speech.mp3")

Availability

The share of requests to this model that completed successfully over the last 30 days. When an upstream provider errors, the gateway retries against another provider serving the same model, so a single provider incident does not necessarily show up here.

Requests (30 days)
4
A success rate is shown from 100 completed requests
Days with traffic
2
of the last 30 days

Frequently asked questions

What is Fish Audio S2.1-Pro?
Fish Audio's recommended production TTS model and an improved version of S2-Pro, with natural-language bracket control and multi-speaker dialogue.
How much does Fish Audio S2.1-Pro cost?
Fish Audio S2.1-Pro costs $0.006 per 1K characters on Oxyy. That is the pay-as-you-go price after the current 60% discount (Launch Promo; standard price $0.015). You pay per request, with no subscription.
How do I call Fish Audio S2.1-Pro through the API?
Send a POST request to https://api.oxyy.ai/v1/audio/speech with "model": "s2.1-pro", authenticated with your Oxyy API key. Put the text in "input" and choose a "voice"; the response body is the audio file.
What inputs and outputs does Fish Audio S2.1-Pro support?
Fish Audio S2.1-Pro accepts text and audio as input and returns audio.
What other models does Fish Audio have?
Fish Audio also offers Fish Audio S1, Fish Audio S2.1-Pro Free, Fish Audio S2-Pro and Voice Design 1 through Oxyy.

Alternatives to Fish Audio S2.1-Pro

Models of the same kind from other vendors, closest in price first. Prices are pay-as-you-go on Oxyy, through the same API key.

Explore more models

More models from Fish Audio