# Fish Audio S2 Pro Text to Speech - Documentation

> For the complete documentation index, see [llms.txt](/llms.txt). Markdown is available with `Accept: text/markdown` and `.md` URL variants.

Source: /docs/api-reference/model-apis-fish-audio-s2-pro-text-to-speech

# Fish Audio S2 Pro Text to Speech

POST

/

v3

/

fish-audio-s2-pro-text-to-speech

Fish Audio S2 Pro Text to Speech

cURL

```
curl --request POST \
--url https://api.novita.ai/v3/fish-audio-s2-pro-text-to-speech \
--header 'Authorization: <authorization>' \
--header 'Content-Type: <content-type>' \
--data '
{
"text": "<string>",
"top_p": 123,
"format": "<string>",
"latency": "<string>",
"prosody": {
"speed": 123,
"volume": 123,
"normalize_loudness": true
},
"normalize": true,
"references": [
{
"text": "<string>",
"audio": "<string>"
}
],
"mp3_bitrate": 123,
"sample_rate": 123,
"temperature": 123,
"chunk_length": 123,
"opus_bitrate": 123,
"reference_id": "<string>",
"max_new_tokens": 123,
"min_chunk_length": 123,
"repetition_penalty": 123,
"early_stop_threshold": 123,
"condition_on_previous_chunks": true
}
'
```

Fish Audio S2 Pro text-to-speech model converts text into natural speech with support for reference voices, sampling controls, chunking, audio formats, and prosody controls.

##

[​](#request-headers)

Request Headers

[​](#param-content-type)

Content-Type

string

required

Supports: `application/json`

[​](#param-authorization)

Authorization

string

required

Bearer authentication format, for example: Bearer {{API Key}}.

##

[​](#request-body)

Request Body

[​](#param-text)

text

string

required

Text to convert to speech. S2-Pro multi-speaker text can use tags such as <|speaker:0|>Hello<|speaker:1|>Hi.

[​](#param-top-p)

top_p

number

Nucleus sampling diversity control.Value range: [0, 1]

[​](#param-format)

format

string

default:"mp3"

Output audio format.Optional values: `wav`, `pcm`, `mp3`, `opus`

[​](#param-latency)

latency

string

default:"normal"

Latency profile.Optional values: `low`, `normal`, `balanced`

[​](#param-prosody)

prosody

object

Prosody controls.

Hide properties

[​](#param-speed)

speed

number

default:1

Speech speed multiplier.

[​](#param-volume)

volume

number

default:0

Volume adjustment.

[​](#param-normalize-loudness)

normalize_loudness

boolean

default:true

Normalize output loudness.

[​](#param-normalize)

normalize

boolean

default:true

Normalize English and Chinese text before synthesis.

[​](#param-references)

references

object[]

Reference audio samples for zero-shot voice cloning.

Hide properties

[​](#param-text-1)

text

string

Transcript for the reference audio.

[​](#param-audio)

audio

string

Reference audio as base64 or URL, depending on provider support.

[​](#param-mp3-bitrate)

mp3_bitrate

integer

default:128

MP3 bitrate in kbps.Optional values: `64`, `128`, `192`

[​](#param-sample-rate)

sample_rate

integer

Output sample rate in Hz. Null uses format default, 44100 Hz or 48000 Hz for opus.

[​](#param-temperature)

temperature

number

Expressiveness control.Value range: [0, 1]

[​](#param-chunk-length)

chunk_length

integer

default:300

Text segment size.Value range: [100, 300]

[​](#param-opus-bitrate)

opus_bitrate

integer

Opus bitrate in bps. -1000 means automatic.Optional values: `-1000`, `24000`, `32000`, `48000`, `64000`

[​](#param-reference-id)

reference_id

string

Voice model ID. For multi-speaker use, pass an array matching speaker indices.

[​](#param-max-new-tokens)

max_new_tokens

integer

default:1024

Maximum audio tokens per chunk.

[​](#param-min-chunk-length)

min_chunk_length

integer

default:50

Minimum characters before splitting text.Value range: [0, 100]

[​](#param-repetition-penalty)

repetition_penalty

number

Penalty to reduce repeated audio patterns.

[​](#param-early-stop-threshold)

early_stop_threshold

number

default:1

Early stopping threshold.Value range: [0, 1]

[​](#param-condition-on-previous-chunks)

condition_on_previous_chunks

boolean

default:true

Use previous audio chunks as context.

##

[​](#response)

Response

Generated audio.
Format: `binary`

Last modified on July 3, 2026