mirror of
https://github.com/sipeed/picoclaw.git
synced 2026-06-12 18:08:54 +00:00
Orkun Manap
dd9adf8a04
* feat: add ElevenLabs Scribe STT transcriber and Telegram SendVoice support
Add ElevenLabsTranscriber as an alternative speech-to-text provider using
the ElevenLabs Scribe API (scribe_v1). This enables voice message
transcription for users who already have an ElevenLabs API key, without
requiring a separate Groq account.
Changes:
- Add ElevenLabsTranscriber implementing the Transcriber interface
- Update DetectTranscriber to check providers.elevenlabs.api_key first,
falling back to Groq for backward compatibility
- Add ElevenLabs to ProvidersConfig
- Add "voice" media type for OGG files with "voice" in filename
- Add SendVoice support in Telegram channel for voice bubble messages
- Add comprehensive tests for ElevenLabs transcriber
Configuration:
"providers": {
"elevenlabs": {
"api_key": "sk_your_key_here"
}
}
Closes #1503 (partial)
* fix: move voice-bubble detection into Telegram channel to avoid regression in other channels
Address review feedback: keep inferMediaType returning "audio" for all
OGG files. Voice-bubble detection (SendVoice vs SendAudio) is now done
inside the Telegram channel based on filename, so other channels that
map "audio" explicitly are unaffected.
* fix: align VoiceConfig struct tags to pass golines formatter
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(agent): use ModelName in loop test added by upstream
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
69 lines
2.2 KiB
Go
69 lines
2.2 KiB
Go
package voice
|
|
|
|
import (
|
|
"context"
|
|
"strings"
|
|
|
|
"github.com/sipeed/picoclaw/pkg/config"
|
|
"github.com/sipeed/picoclaw/pkg/providers"
|
|
)
|
|
|
|
type Transcriber interface {
|
|
Name() string
|
|
Transcribe(ctx context.Context, audioFilePath string) (*TranscriptionResponse, error)
|
|
}
|
|
|
|
type TranscriptionResponse struct {
|
|
Text string `json:"text"`
|
|
Language string `json:"language,omitempty"`
|
|
Duration float64 `json:"duration,omitempty"`
|
|
}
|
|
|
|
func supportsAudioTranscription(model string) bool {
|
|
protocol, _ := providers.ExtractProtocol(model)
|
|
|
|
switch protocol {
|
|
case "openai", "azure", "azure-openai",
|
|
"litellm", "openrouter", "groq", "zhipu", "gemini", "nvidia",
|
|
"ollama", "moonshot", "shengsuanyun", "deepseek", "cerebras",
|
|
"vivgrid", "volcengine", "vllm", "qwen", "qwen-intl", "qwen-international", "dashscope-intl",
|
|
"qwen-us", "dashscope-us", "mistral", "avian", "minimax", "longcat", "modelscope", "novita",
|
|
"coding-plan", "alibaba-coding", "qwen-coding":
|
|
// These protocols all go through the OpenAI-compatible or Azure provider path in
|
|
// providers.CreateProviderFromConfig, so they are the only ones that can supply
|
|
// the audio media payload shape expected by NewAudioModelTranscriber.
|
|
|
|
// TODO: Further restrict this by modelID, since not every model under these
|
|
// protocols supports audio transcription.
|
|
return true
|
|
default:
|
|
return false
|
|
}
|
|
}
|
|
|
|
// DetectTranscriber inspects cfg and returns the appropriate Transcriber, or
|
|
// nil if no supported transcription provider is configured.
|
|
func DetectTranscriber(cfg *config.Config) Transcriber {
|
|
if modelName := strings.TrimSpace(cfg.Voice.ModelName); modelName != "" {
|
|
modelCfg, err := cfg.GetModelConfig(modelName)
|
|
if err != nil {
|
|
return nil
|
|
}
|
|
if supportsAudioTranscription(modelCfg.Model) {
|
|
return NewAudioModelTranscriber(modelCfg)
|
|
}
|
|
}
|
|
|
|
// ElevenLabs voice config (supports Scribe STT).
|
|
if key := strings.TrimSpace(cfg.Voice.ElevenLabsAPIKey); key != "" {
|
|
return NewElevenLabsTranscriber(key)
|
|
}
|
|
// Fall back to any model-list entry that uses the groq/ protocol.
|
|
for _, mc := range cfg.ModelList {
|
|
if strings.HasPrefix(mc.Model, "groq/") && mc.APIKey() != "" {
|
|
return NewGroqTranscriber(mc.APIKey())
|
|
}
|
|
}
|
|
return nil
|
|
}
|