Documentation
¶
Overview ¶
Package revai wraps Rev AI's speech-to-text API.
NewTranscriptionModel orchestrates Rev AI's async /v1/jobs flow (submit → poll → fetch). Rev AI's strength is enterprise- grade accuracy on English / multilingual content plus rich metadata (speaker channels, custom vocabularies, profanity filter, language ID).
Set language through transcription.Options.Language and select machine or human transcription through transcription.Options.Model. Provider extras such as speaker_channels_count, custom_vocabulary_id, and remove_disfluencies belong in Options.Extensions under RequestExtensionKey.
See https://docs.rev.ai/ for the full reference.
Index ¶
Examples ¶
Constants ¶
const ( RequestExtensionKey = Provider + "/request" ResponseExtensionKey = Provider + "/response" DefaultBaseURL = "https://api.rev.ai/speechtotext/v1" DefaultPollInterval = 3 * time.Second DefaultPollTimeout = 30 * time.Minute )
const ( ModelMachine = "machine" ModelHuman = "human" )
const (
Provider = "revai"
)
Provider is the stable backend name for host-side attribution.
Variables ¶
This section is empty.
Functions ¶
This section is empty.
Types ¶
type TranscriptionModel ¶ added in v0.41.0
type TranscriptionModel struct {
// contains filtered or unexported fields
}
TranscriptionModel wraps Rev AI's async transcription flow. Rev is async-only: Call submits the audio, polls /jobs/{id} until "transcribed", then fetches the plain-text transcript.
Language and transcriber selection use transcription.Options.Language and transcription.Options.Model (ModelMachine or ModelHuman). Diarization, custom vocabularies, and profanity filtering use Options.Extensions under RequestExtensionKey. Audio.Source alone chooses the media location. URI sources use source_config.url; the native source_config extension may supply auth_headers only, for URI audio.
func NewTranscriptionModel ¶ added in v0.41.0
func NewTranscriptionModel(ctx context.Context, config TranscriptionModelConfig) (*TranscriptionModel, error)
func (*TranscriptionModel) Call ¶ added in v0.41.0
func (t *TranscriptionModel) Call(ctx context.Context, req *transcription.Request) (*transcription.Response, error)
type TranscriptionModelConfig ¶ added in v0.41.0
type TranscriptionModelConfig struct {
APIKey string
DefaultOptions transcription.Options
BaseURL string
HTTPClient *http.Client
PollInterval time.Duration
PollTimeout time.Duration
}
Example ¶
package main
import (
"context"
"fmt"
"github.com/Tangerg/scope/core/transcription"
"github.com/Tangerg/scope/models/revai"
)
func main() {
options := transcription.Options{Model: revai.ModelMachine, Language: "en"}
_, err := revai.NewTranscriptionModel(context.Background(), revai.TranscriptionModelConfig{
APIKey: "example-key", DefaultOptions: options,
})
fmt.Println(options.Model, options.Language, err)
}
Output: machine en <nil>
func (TranscriptionModelConfig) Validate ¶ added in v0.41.0
func (t TranscriptionModelConfig) Validate() error
Source Files