dto/audio.go

package dto

import (
	"encoding/json"

	"github.com/QuantumNous/new-api/types"

	"github.com/gin-gonic/gin"
)

type AudioRequest struct {
	Model          string          `json:"model"`
	Input          string          `json:"input"`
	Voice          string          `json:"voice"`
	Instructions   string          `json:"instructions,omitempty"`
	ResponseFormat string          `json:"response_format,omitempty"`
	Speed          float64         `json:"speed,omitempty"`
	StreamFormat   string          `json:"stream_format,omitempty"`
	Metadata       json.RawMessage `json:"metadata,omitempty"`
}

func (r *AudioRequest) GetTokenCountMeta() *types.TokenCountMeta {
	meta := &types.TokenCountMeta{
		CombineText: r.Input,
		TokenType:   types.TokenTypeTextNumber,
	}
	return meta
}

func (r *AudioRequest) IsStream(c *gin.Context) bool {
	return false
}

func (r *AudioRequest) SetModelName(modelName string) {
	if modelName != "" {
		r.Model = modelName
	}
}

type AudioResponse struct {
	Text string `json:"text"`
}

type WhisperVerboseJSONResponse struct {
	Task     string    `json:"task,omitempty"`
	Language string    `json:"language,omitempty"`
	Duration float64   `json:"duration,omitempty"`
	Text     string    `json:"text,omitempty"`
	Segments []Segment `json:"segments,omitempty"`
}

type Segment struct {
	Id               int     `json:"id"`
	Seek             int     `json:"seek"`
	Start            float64 `json:"start"`
	End              float64 `json:"end"`
	Text             string  `json:"text"`
	Tokens           []int   `json:"tokens"`
	Temperature      float64 `json:"temperature"`
	AvgLogprob       float64 `json:"avg_logprob"`
	CompressionRatio float64 `json:"compression_ratio"`
	NoSpeechProb     float64 `json:"no_speech_prob"`
}