Fish Audio: Fish Audio S2.1-Pro

Name: Fish Audio S2.1-Pro
Author: Fish Audio

fish/s2-1-pro

activo tts 1 proveedor

Playground

Fish Audio's recommended production text-to-speech model (S2.1-Pro) with improved quality, latency and throughput over S2-Pro, plus a free variant (s2.1-pro-free) under fair-use limits.

AutorFish Audio

Idiomas1 idiomas

VocesCargando...

Formatos de respuestaMP3 · WAV · PCM · Opus

Modelos variantes2 IDs

Estadoactivo

Inicio rápido

Fish Audio S2.1-Pro

Crea una clave API

Regístrate en AllModels, crea una clave API y guárdala como ALLMODELS_API_KEY.

Crear clave API

Haz una solicitud

Elige un SDK, un modo de solicitud y un lenguaje. El modelo y la ruta del proveedor ya están completados.

TTS en streaming con el ElevenLabs SDK

Enruta el ElevenLabs SDK a través de AllModels y transmite la respuesta de audio.

import { ElevenLabsClient } from "elevenlabs";

const client = new ElevenLabsClient({
  apiKey: process.env.ALLMODELS_API_KEY,
  baseUrl: "https://api.allmodels.io/el"
});

const stream = await client.textToSpeech.stream("voice_id", {
  text: "I'm sorry, Dave. I'm afraid I can't do that.",
  modelId: "fish/s2-1-pro",
  outputFormat: "mp3_44100_128"
}, {
  queryParams: {
    provider: {
      "only": [
        "fish"
      ]
    }
  }
});

const reader = stream.getReader();
for (;;) {
  const { done, value } = await reader.read();
  if (done) break;
  // Write value to your response, file, or audio playback pipeline.
}

Pasa parámetros del proveedor

Pasa las preferencias de provider mediante las opciones de solicitud del SDK compatible cuando quieras fijar una ruta a un proveedor.

{
  queryParams: {
    provider: {
      only: ["fish"]
    }
  }
}

Modelos variantes

Son IDs de modelo nativos que el autor o proveedor acepta para la misma familia de modelos canónica.

Fish Audio S2.1-Pro Default

Recommended production Fish Audio TTS model; improved quality, latency, and throughput over S2-Pro.

s2.1-pro

Fish Audio S2.1-Pro Free Variant

Same model as S2.1-Pro billed at $0 for testing/dev/small business under fair-use limits.

s2.1-pro-free

Proveedores

Distintos proveedores pueden alojar el mismo modelo. Elige un proveedor cuando necesites un backend fijo, o deja que el enrutamiento elija entre ellos.

ProveedorSlugPor 1k caracteresLatenciaiModosDisponibilidad

Fish Audio 19 parámetros

fish

Desde $0,015

—

Síncrono · Streaming

Fish Audio

19 parámetros de proveedor documentados para esta ruta.

Precios

ModoIdiomaPor 1k caracteres

Text To Speech (Paid) Cualquiera $0,015 ($15.00 usd Per 1m Utf8 Bytes)

Free Tier Cualquiera $0 ($0.00 usd Per 1m Utf8 Bytes)

Parámetros

model header · string · obligatorio

Specify which TTS model to use. We recommend `s2-pro`.

predeterminado "s2-pro"2 valores enum

Valores

s1s2-pro

text body · string · obligatorio

Text to convert to speech.

chunk_length body · integer · opcional

Text segment size for processing.

predeterminado 300mín. 100máx. 300

condition_on_previous_chunks body · boolean · opcional

Use previous audio as context for voice consistency.

predeterminado true

early_stop_threshold body · number · opcional

Early stopping threshold for batch processing.

predeterminado 1mín. 0máx. 1

format body · string · opcional

Output audio format.

predeterminado "mp3"4 valores enum

Valores

wavpcmmp3opus

latency body · string · opcional

Latency-quality trade-off. normal: best quality, balanced: reduced latency, low: lowest latency.

predeterminado "normal"3 valores enum

Valores

lownormalbalanced

max_new_tokens body · integer · opcional

Maximum audio tokens to generate per text chunk.

predeterminado 1024

min_chunk_length body · integer · opcional

Minimum characters before splitting into a new chunk.

predeterminado 50mín. 0máx. 100

mp3_bitrate body · integer · opcional

MP3 bitrate in kbps. Only applies when format is mp3.

predeterminado 1283 valores enum

Valores

64128192

normalize body · boolean · opcional

Normalizes text for English and Chinese, improving stability for numbers.

predeterminado true

opus_bitrate body · integer · opcional

Opus bitrate in bps. -1000 for automatic. Only applies when format is opus.

predeterminado -10005 valores enum

Valores

-100024000320004800064000

prosody body · object | null · opcional

Speed and volume adjustments for the output.

predeterminado null

reference_id body · string | array | null · opcional

Voice model ID(s) from Fish Audio library or your custom models. For single-speaker synthesis, provide a string. For multi-speaker synthesis (dialogue), provide an array of model IDs. **Multi-speaker is only available with the S2-Pro model.** When using multiple speakers, use speaker tags in your text like `<|speaker:0|>` and `<|speaker:1|>` to indicate speaker changes. Example: `<|speaker:0|>Hello!<|speaker:1|>Hi there!<|speaker:0|>How are you?` with `reference_id: ["speaker-a-id", "speaker-b-id"]`.

predeterminado null

references body · array | array | null · opcional

Inline voice references for zero-shot cloning. Requires MessagePack (not JSON). For single speaker, provide an array of ReferenceAudio objects. For multiple speakers, provide an array of arrays where each inner array contains references for one speaker. **Multi-speaker is only available with the S2-Pro model.** The speaker index corresponds to the index in reference_id array. Example for multi-speaker: [[{audio, text}], [{audio, text}, {audio, text}]] for 2 speakers where speaker 1 has 2 reference samples.

repetition_penalty body · number · opcional

Penalty for repeating audio patterns. Values above 1.0 reduce repetition.

predeterminado 1.2

sample_rate body · integer | null · opcional

Audio sample rate in Hz. When null, uses the format's default (44100 Hz for most formats, 48000 Hz for opus).

predeterminado null

temperature body · number · opcional

Controls expressiveness. Higher is more varied, lower is more consistent.

predeterminado 0.7mín. 0máx. 1

top_p body · number · opcional

Controls diversity via nucleus sampling.

predeterminado 0.7mín. 0máx. 1

Idiomas admitidos

1 idiomas

English en

Voces

Funciones

Text to speech

Generates spoken audio from text input.

text_to_speech

Streaming

Supports streaming audio output (HTTP + WebSocket) with optional timestamps.

streaming

Synchronous

Synthesizes speech from fully-submitted text in a single synchronous request.

synchronous

Multilingual

Supports 83 languages.

multilingual

Voice cloning

Supports instant (reference audio) and persistent (reference_id) voice cloning.

voice_cloning

Emotion / expression control

Natural-language and bracket expression control; multi-speaker.

emotion_control

Código

TTS en streaming con el ElevenLabs SDK

Enruta el ElevenLabs SDK a través de AllModels y transmite la respuesta de audio.

import { ElevenLabsClient } from "elevenlabs";

const client = new ElevenLabsClient({
  apiKey: process.env.ALLMODELS_API_KEY,
  baseUrl: "https://api.allmodels.io/el"
});

const stream = await client.textToSpeech.stream("voice_id", {
  text: "I'm sorry, Dave. I'm afraid I can't do that.",
  modelId: "fish/s2-1-pro",
  outputFormat: "mp3_44100_128"
}, {
  queryParams: {
    provider: {
      "only": [
        "fish"
      ]
    }
  }
});

const reader = stream.getReader();
for (;;) {
  const { done, value } = await reader.read();
  if (done) break;
  // Write value to your response, file, or audio playback pipeline.
}