Skip to main content

​
fishaudio.types.voices

Voice and model management types.

​
Sample Objects

class Sample(BaseModel)
A sample audio for a voice model.

​
Author Objects

class Author(BaseModel)
Voice model author information.

​
Voice Objects

class Voice(BaseModel)
A voice model Represents a TTS voice that can be used for synthesis.

​
fishaudio.types.tts

TTS-related types.

​
ReferenceAudio Objects

class ReferenceAudio(BaseModel)
Reference audio for voice cloning/style.

​
Prosody Objects

class Prosody(BaseModel)
Speech prosody settings (speed and volume).

​
TTSConfig Objects

class TTSConfig(BaseModel)
TTS generation configuration. Reusable configuration for text-to-speech requests. Create once, use multiple times. All parameters have sensible defaults.

​
TTSRequest Objects

class TTSRequest(BaseModel)
Request parameters for text-to-speech generation. This model is used internally for WebSocket streaming. For the HTTP API, parameters are passed directly to methods.

​
StartEvent Objects

class StartEvent(BaseModel)
WebSocket start event.

​
TextEvent Objects

class TextEvent(BaseModel)
WebSocket text chunk event.

​
FlushEvent Objects

class FlushEvent(BaseModel)
WebSocket flush event - forces buffer to generate audio immediately.

​
CloseEvent Objects

class CloseEvent(BaseModel)
WebSocket close event.

​
fishaudio.types.account

Account-related types (credits, packages, etc.).

​
Credits Objects

class Credits(BaseModel)
User’s API credit balance.

​
Package Objects

class Package(BaseModel)
User’s prepaid package information.

​
fishaudio.types.asr

ASR (Automatic Speech Recognition) related types.

​
ASRSegment Objects

class ASRSegment(BaseModel)
A timestamped segment of transcribed text.

​
ASRResponse Objects

class ASRResponse(BaseModel)
Response from speech-to-text transcription.

​
duration

Duration in milliseconds

​
fishaudio.types.shared

Shared types used across the SDK.

​
PaginatedResponse Objects

class PaginatedResponse(BaseModel, Generic[T])
Generic paginated response.