stemedb/cmd/pitch-voiceover/pkg/elevenlabs/voice_design.go
jordan 157dbbb9eb feat: Complete Aphoria Phase 8-9 + UAT suite (90/90 tests passing)
## Phase 8: Enterprise Extractor Improvements 
- 14 security extractors (TLS, JWT, SQL injection, XSS, etc.)
- 10 framework-specific extractors (Spring, Django, Rails, etc.)
- Config file security detection (YAML, TOML)

## Phase 9: Autonomous Extractor Generation 
- Shadow mode executor with TP/FP tracking
- Graduation pipeline with confidence thresholds
- Auto-rollback on regression detection
- Cross-project pattern syncing

## UAT Suite Complete (14 scripts, 90 tests)
- test-core-detection.sh (6 tests)
- test-declarative-extractors.sh (5 tests)
- test-domain-frameworks.sh (5 tests)
- test-domain-unreal.sh (3 tests)
- test-llm-extraction.sh (6 tests)
- test-eval-harness.sh (5 tests)
- test-cross-language.sh (3 tests)
- test-precommit-performance.sh (4 tests)
- test-output-formats.sh (8 tests)
- test-drift-detection.sh (6 tests)
- test-exit-codes.sh (12 tests)
+ 3 more scripts

## Other Changes
- Updated roadmap to mark Phase 8-9 complete
- Added .gitignore entries for build artifacts
- Updated pre-commit: 800 line limit, exclude tests/data/cmd

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-02-06 22:50:55 -07:00

97 lines
2.7 KiB
Go

package elevenlabs
import (
"context"
"encoding/json"
"fmt"
"net/http"
)
const (
// DefaultVoiceDesignModel is the default model for voice design.
DefaultVoiceDesignModel = "eleven_multilingual_ttv_v2"
// DefaultGuidanceScale balances prompt adherence with audio quality.
DefaultGuidanceScale = 5.0
// DefaultLoudness is the default volume level.
DefaultLoudness = 0.5
)
// DesignVoice generates voice previews from a text description.
// Returns typically 3 voice previews to choose from.
func (c *Client) DesignVoice(ctx context.Context, req VoiceDesignRequest) (*VoiceDesignResponse, error) {
if req.VoiceDescription == "" {
return nil, fmt.Errorf("%w: voice description is required", ErrInvalidConfig)
}
if len(req.VoiceDescription) < 20 || len(req.VoiceDescription) > 1000 {
return nil, fmt.Errorf("%w: voice description must be 20-1000 characters", ErrInvalidConfig)
}
// Set defaults
if req.ModelID == "" {
req.ModelID = DefaultVoiceDesignModel
}
if req.GuidanceScale == 0 {
req.GuidanceScale = DefaultGuidanceScale
}
if req.Loudness == 0 {
req.Loudness = DefaultLoudness
}
// If no text provided, enable auto-generation
if req.Text == "" {
req.AutoGenerateText = true
}
respBody, err := c.doRequest(ctx, http.MethodPost, "/text-to-voice/design", req)
if err != nil {
return nil, fmt.Errorf("design voice: %w", err)
}
var resp VoiceDesignResponse
if err := json.Unmarshal(respBody, &resp); err != nil {
return nil, fmt.Errorf("unmarshal voice design response: %w", err)
}
return &resp, nil
}
// SaveDesignedVoice saves a voice preview as a permanent voice.
// The GeneratedVoiceID comes from a VoicePreview returned by DesignVoice.
func (c *Client) SaveDesignedVoice(ctx context.Context, req SaveVoiceRequest) (*SaveVoiceResponse, error) {
if req.VoiceName == "" {
return nil, fmt.Errorf("%w: voice name is required", ErrInvalidConfig)
}
if req.GeneratedVoiceID == "" {
return nil, fmt.Errorf("%w: generated voice ID is required", ErrInvalidConfig)
}
respBody, err := c.doRequest(ctx, http.MethodPost, "/text-to-voice/create-voice-from-preview", req)
if err != nil {
return nil, fmt.Errorf("save designed voice: %w", err)
}
var resp SaveVoiceResponse
if err := json.Unmarshal(respBody, &resp); err != nil {
return nil, fmt.Errorf("unmarshal save voice response: %w", err)
}
return &resp, nil
}
// DeleteVoice removes a voice from the account.
func (c *Client) DeleteVoice(ctx context.Context, voiceID string) error {
if voiceID == "" {
return fmt.Errorf("%w: voice ID is required", ErrInvalidConfig)
}
path := fmt.Sprintf("/voices/%s", voiceID)
_, err := c.doRequest(ctx, http.MethodDelete, path, nil)
if err != nil {
return fmt.Errorf("delete voice: %w", err)
}
return nil
}