Files
new-api/relaykit/dto/audio.go
T
CaIon 14a9acd368 feat(custom): CNY native billing, daily check-in button, subscription plans page, usage docs and promo banner
Based on QuantumNous/new-api v1.0.0-rc.36 (shallow history squashed).

- CNY quota display mode: RMB-denominated top-up and crediting across Epay/Waffo channels
- New CheckinButton in both authenticated and public headers (Turnstile supported)
- New /subscribe page with public plan snapshot, Alipay/balance payment, auto group upgrade/reset
- New /docs 12-section beginner guide with anchor navigation
- New home PromoBanner linking to /docs; i18n synced (en/zh/zh-TW/fr/ja/ru/vi)
- README: document custom features, live demo https://ai.88531.cn
2026-09-23 16:28:52 +08:00

77 lines
2.5 KiB
Go
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
package dto
import (
"encoding/json"
"net/http"
"strings"
"github.com/QuantumNous/new-api/relaykit/types"
)
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"`
// vllm-omini
TaskType json.RawMessage `json:"task_type,omitempty"`
Language json.RawMessage `json:"language,omitempty"`
RefAudio json.RawMessage `json:"ref_audio,omitempty"`
RefText json.RawMessage `json:"ref_text,omitempty"`
XVectorOnlyMode json.RawMessage `json:"x_vector_only_mode,omitempty"`
MaxNewTokens json.RawMessage `json:"max_new_tokens,omitempty"`
InitialCodecChunkFrames json.RawMessage `json:"initial_codec_chunk_frames,omitempty"`
// TODO:ensure that the logic remains correct after the stream is started.
//Stream json.RawMessage `json:"stream,omitempty"`
}
func (r *AudioRequest) GetTokenCountMeta() *types.TokenCountMeta {
meta := &types.TokenCountMeta{
CombineText: r.Input,
TokenType: types.TokenTypeTextNumber,
}
if strings.Contains(r.Model, "gpt") {
meta.TokenType = types.TokenTypeTokenizer
}
return meta
}
func (r *AudioRequest) IsStream(c *http.Request) bool {
return r.StreamFormat == "sse"
}
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"`
}