MODEL ID fishaudio:s2.1@pro

coming-soon

Fish Audio S2.1 Pro

by Fish Audio March 1, 2026

Fish Audio S2.1 Pro is a flagship text-to-speech model built for highly expressive, low-latency speech generation. It supports natural-language bracket cues for emotion and delivery control, multi-speaker dialogue in a single generation, 80+ languages with automatic language detection, and realtime streaming with very fast time to first audio.

API Options

Platform-level options for task execution and delivery.

taskType string required value: audioInference: Identifier for the type of task being performed

taskUUID string required UUID v4: UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

outputType string default: URL: Audio output type.

Allowed values 3 values

outputFormat string default: MP3

Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities.

`MP3`: Compressed audio, smaller file size.
`WAV`: Uncompressed, high-quality audio.
`FLAC`: Lossless compression.
`OGG`: Open-source compressed audio format (Vorbis codec).

Allowed values 4 values

audioSettings object

Audio encoding settings for controlling the bitrate, number of channels, and sample rate of the generated audio. Only applicable for lossy output formats (MP3 and OGG). When using lossless formats (WAV or FLAC), this parameter must not be provided.

The available sample rates and valid bitrate ranges depend on the output format. For OGG, bitrate limits also vary by the number of channels.

MP3 bitrate limits

Bitrate limits for MP3 are the same regardless of mono or stereo.

Sample Rate	Min Bitrate	Max Bitrate
8,000 Hz	8 kbps	64 kbps
11,025 Hz	8 kbps	64 kbps
12,000 Hz	8 kbps	64 kbps
16,000 Hz	8 kbps	160 kbps
22,050 Hz	8 kbps	160 kbps
24,000 Hz	8 kbps	160 kbps
32,000 Hz	32 kbps	320 kbps
44,100 Hz	32 kbps	320 kbps
48,000 Hz	32 kbps	320 kbps

OGG bitrate limits — Mono (1 channel)

Sample Rate	Min Bitrate	Max Bitrate
8,000 Hz	8 kbps	40 kbps
12,000 Hz	16 kbps	48 kbps
16,000 Hz	16 kbps	96 kbps
24,000 Hz	16 kbps	80 kbps
48,000 Hz	32 kbps	224 kbps

OGG bitrate limits — Stereo (2 channels)

Sample Rate	Min Bitrate	Max Bitrate
8,000 Hz	16 kbps	80 kbps
12,000 Hz	16 kbps	96 kbps
16,000 Hz	24 kbps	192 kbps
24,000 Hz	32 kbps	160 kbps
48,000 Hz	48 kbps	256 kbps

Lossless formats: When outputFormat is set to WAV or FLAC, the audioSettings parameter is not available since these formats produce uncompressed or lossless audio with no configurable encoding settings.

Properties 3 properties

audioSettings » bitrate bitrate integer min: 8: Audio bitrate in kbps.

audioSettings » channels channels integer default: 2: Number of audio channels. 1 for mono, 2 for stereo.

Allowed values 2 values

audioSettings » sampleRate sampleRate integer: Audio sample rate in Hz.

webhookURL string URI

Specifies a webhook URL where JSON responses will be sent via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.

Learn more 1 resource

Webhooks
PLATFORM

deliveryMethod string default: sync

Determines how the API delivers task results.

Allowed values 2 values

: Returns complete results directly in the API response.
: Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

Learn more 1 resource

Task Polling
PLATFORM

uploadEndpoint string URI

Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials.

Common use cases:

Cloud storage: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.
CDN integration: Upload to content delivery networks for immediate distribution.

// S3 presigned URL for secure upload
https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600

// Google Cloud Storage presigned URL
https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789

// Custom storage endpoint
https://storage.example.com/uploads/generated-image.jpg

The content data will be sent as the request body to the specified URL when generation is complete.

ttl integer min: 60: Time-to-live (TTL) in seconds for generated content. Only applies when outputType is URL.

includeCost boolean default: false: Include task cost in the response.

numberResults integer min: 1 max: 4 default: 1: Number of results to generate. Each result uses a different seed, producing variations of the same parameters.

Inputs

Input resources for the task (images, audio, etc). These must be nested inside the inputs object.

inputs » referenceVoices referenceVoices array of objects items: 1

Inline voice reference for zero-shot voice cloning. Single-speaker only.

Properties 2 properties

inputs » referenceVoices » audio audio string required: Reference audio clip for the voice to clone (UUID, URL, DataURI, or Base64). Audio duration must be between 1.0 and 90.0 seconds.

inputs » referenceVoices » text text string required min: 1 max: 1000: Transcript of the reference audio clip. Must match the spoken content of the reference audio.

Core Parameters

Primary parameters that define the task output.

model string required value: fishaudio:s2.1@pro: Identifier of the model to use for generation.

speech object required

Settings for speech generation.

Properties 5 properties

speech » text text string required min: 1 max: 3000: Text to convert to speech. For multi-speaker dialogue, embed inline speaker tags such as <|speaker:0|> and <|speaker:1|>. Bracket-style paralinguistic cues such as [laughs], [sigh], [short pause], and [whispering] can also be embedded inline.

speech » voice voice string

Voice model ID from the Fish Audio voice library or a custom voice. Browse all available voices at https://api.fish.audio/model?page_size=100&page_number=1&sort_by=score.

Allowed values 8 values

: Egirl — A cute e-girl to chat with you.
: Selene — A meditative female voice.
: Adrian — A steady and reliable narrator.
: Sarah — An engaged speaker.
: Ethan — A curious explainer.
: Laura — A confident female narrator.
: Jordan — A motivational speaker.
: Hannah — A conversation specialist.

speech » voices voices array of strings items: 2: Voice model IDs for multi-speaker dialogue. Speaker tags in speech.text such as <|speaker:0|> and <|speaker:1|> map to the matching array index.

speech » volume volume float default: 0: Volume adjustment in decibels. 0 = no change.

speech » speed speed float min: 0.5 max: 2 step: 0.01 default: 1: Playback speed of the generated speech.

Settings

Technical parameters to fine-tune the inference process. These must be nested inside the settings object.

settings » temperature temperature float min: 0 max: 1 step: 0.01 default: 0.7: Expressiveness of the generated speech.

settings » topP topP float min: 0.0001 max: 1 step: 0.01 default: 0.7: Nucleus sampling parameter that controls diversity by limiting the probability mass. Lower values make outputs more focused, higher values increase diversity.

settings » chunkLength chunkLength integer min: 100 max: 300 default: 300: Text segment size for processing.

settings » conditionOnPreviousChunks conditionOnPreviousChunks boolean default: true: Previous audio context for voice consistency across chunks.

settings » earlyStopThreshold earlyStopThreshold float min: 0 max: 1 default: 1: Early stopping threshold for batch processing.

settings » latency latency string default: normal

Latency / quality trade-off.

Allowed values 3 values

: Fastest response, lower quality.
: Balanced default.
: Highest quality, slower.

settings » maxTokens maxTokens integer min: 1 max: 4294967295 default: 1024: Maximum audio tokens to generate per text chunk.

settings » minChunkLength minChunkLength integer min: 0 max: 100 default: 50: Minimum characters before splitting into a new chunk.

settings » normalize normalize boolean default: true: Text normalization for English and Chinese. Improves stability for numbers.

settings » normalizeLoudness normalizeLoudness boolean default: true: Normalize output loudness for consistent perceived volume.

settings » repetitionPenalty repetitionPenalty float min: 0 max: 2 step: 0.01 default: 1.2: Penalty for repeating audio patterns.