Feat/speech support (#392)

* feat: expand speech provider support with new client types and configuration schema

* feat: add icon support for speech providers and update related configurations

* feat: add SVG support for Deepgram and Elevenlabs with Vue components

* feat: except *-speech client type in llm provider

* feat: enhance speech provider functionality with advanced settings and model import capabilities

* chore: remove go.mod replace

* feat: enhance speech provider functionality with advanced settings and model import capabilities

* chore: update go module dependencies

* feat: Ear and Mouth

* fix: separate ear/mouth page

* fix: separate audio domain and restore transcription templates

Move speech and transcription internals into the audio domain, restore template-driven transcription providers, and regenerate Swagger/SDK so the frontend can stop hand-calling /transcription-* APIs.

---------

Co-authored-by: aki <arisu@ieee.org>

db/migrations/0001_init.up.sql

@@ -77,13 +77,19 @@ CREATE TABLE IF NOT EXISTS providers (
     'github-copilot',
     'edge-speech',
     'openai-speech',
+    'openai-transcription',
     'openrouter-speech',
+    'openrouter-transcription',
     'elevenlabs-speech',
+    'elevenlabs-transcription',
     'deepgram-speech',
+    'deepgram-transcription',
     'minimax-speech',
     'volcengine-speech',
     'alibabacloud-speech',
-    'microsoft-speech'
+    'microsoft-speech',
+    'google-speech',
+    'google-transcription'
   ))
 );
 
@@ -108,7 +114,7 @@ CREATE TABLE IF NOT EXISTS models (
   created_at TIMESTAMPTZ NOT NULL DEFAULT now(),
   updated_at TIMESTAMPTZ NOT NULL DEFAULT now(),
   CONSTRAINT models_provider_id_model_id_unique UNIQUE (provider_id, model_id),
-  CONSTRAINT models_type_check CHECK (type IN ('chat', 'embedding', 'speech'))
+  CONSTRAINT models_type_check CHECK (type IN ('chat', 'embedding', 'speech', 'transcription'))
 );
 
 CREATE TABLE IF NOT EXISTS model_variants (
@@ -170,6 +176,7 @@ CREATE TABLE IF NOT EXISTS bots (
   image_model_id UUID REFERENCES models(id) ON DELETE SET NULL,
   discuss_probe_model_id UUID REFERENCES models(id) ON DELETE SET NULL,
   tts_model_id UUID REFERENCES models(id) ON DELETE SET NULL,
+  transcription_model_id UUID REFERENCES models(id) ON DELETE SET NULL,
   browser_context_id UUID REFERENCES browser_contexts(id) ON DELETE SET NULL,
   persist_full_tool_results BOOLEAN NOT NULL DEFAULT false,
   metadata JSONB NOT NULL DEFAULT '{}'::jsonb,

db/migrations/0069_add_transcription_models_and_speech_domain.down.sql

@@ -0,0 +1,33 @@
+-- 0069_add_transcription_models_and_speech_domain
+-- Revert transcription model type and speech-domain expansion.
+
+DELETE FROM models WHERE type = 'transcription';
+DELETE FROM providers WHERE client_type = 'google-speech';
+
+ALTER TABLE models
+  DROP CONSTRAINT IF EXISTS models_type_check;
+
+ALTER TABLE models
+  ADD CONSTRAINT models_type_check CHECK (type IN ('chat', 'embedding', 'speech'));
+
+ALTER TABLE providers
+  DROP CONSTRAINT IF EXISTS providers_client_type_check;
+
+ALTER TABLE providers
+  ADD CONSTRAINT providers_client_type_check CHECK (client_type IN (
+    'openai-responses',
+    'openai-completions',
+    'anthropic-messages',
+    'google-generative-ai',
+    'openai-codex',
+    'github-copilot',
+    'edge-speech',
+    'openai-speech',
+    'openrouter-speech',
+    'elevenlabs-speech',
+    'deepgram-speech',
+    'minimax-speech',
+    'volcengine-speech',
+    'alibabacloud-speech',
+    'microsoft-speech'
+  ));

db/migrations/0069_add_transcription_models_and_speech_domain.up.sql

@@ -0,0 +1,31 @@
+-- 0069_add_transcription_models_and_speech_domain
+-- Expand the speech domain to support transcription models and shared speech providers.
+
+ALTER TABLE providers
+  DROP CONSTRAINT IF EXISTS providers_client_type_check;
+
+ALTER TABLE providers
+  ADD CONSTRAINT providers_client_type_check CHECK (client_type IN (
+    'openai-responses',
+    'openai-completions',
+    'anthropic-messages',
+    'google-generative-ai',
+    'openai-codex',
+    'github-copilot',
+    'edge-speech',
+    'openai-speech',
+    'openrouter-speech',
+    'elevenlabs-speech',
+    'deepgram-speech',
+    'minimax-speech',
+    'volcengine-speech',
+    'alibabacloud-speech',
+    'microsoft-speech',
+    'google-speech'
+  ));
+
+ALTER TABLE models
+  DROP CONSTRAINT IF EXISTS models_type_check;
+
+ALTER TABLE models
+  ADD CONSTRAINT models_type_check CHECK (type IN ('chat', 'embedding', 'speech', 'transcription'));

db/migrations/0070_add_bot_transcription_model.down.sql

@@ -0,0 +1,8 @@
+-- 0070_add_bot_transcription_model
+-- Remove bots.transcription_model_id.
+
+ALTER TABLE bots
+  DROP CONSTRAINT IF EXISTS bots_transcription_model_id_fkey;
+
+ALTER TABLE bots
+  DROP COLUMN IF EXISTS transcription_model_id;

db/migrations/0070_add_bot_transcription_model.up.sql

@@ -0,0 +1,5 @@
+-- 0070_add_bot_transcription_model
+-- Add bots.transcription_model_id for bot-level speech-to-text defaults.
+
+ALTER TABLE bots
+  ADD COLUMN IF NOT EXISTS transcription_model_id UUID REFERENCES models(id) ON DELETE SET NULL;

db/migrations/0071_split_transcription_providers.down.sql

@@ -0,0 +1,33 @@
+-- 0071_split_transcription_providers
+-- Remove dedicated transcription provider client types.
+
+DELETE FROM providers
+WHERE client_type IN (
+  'openai-transcription',
+  'openrouter-transcription',
+  'elevenlabs-transcription',
+  'deepgram-transcription',
+  'google-transcription'
+);
+
+ALTER TABLE providers DROP CONSTRAINT IF EXISTS providers_client_type_check;
+
+ALTER TABLE providers
+ADD CONSTRAINT providers_client_type_check CHECK (client_type IN (
+  'openai-responses',
+  'openai-completions',
+  'anthropic-messages',
+  'google-generative-ai',
+  'openai-codex',
+  'github-copilot',
+  'edge-speech',
+  'openai-speech',
+  'openrouter-speech',
+  'elevenlabs-speech',
+  'deepgram-speech',
+  'minimax-speech',
+  'volcengine-speech',
+  'alibabacloud-speech',
+  'microsoft-speech',
+  'google-speech'
+));

db/migrations/0071_split_transcription_providers.up.sql

@@ -0,0 +1,29 @@
+-- 0071_split_transcription_providers
+-- Add dedicated transcription provider client types.
+
+ALTER TABLE providers DROP CONSTRAINT IF EXISTS providers_client_type_check;
+
+ALTER TABLE providers
+ADD CONSTRAINT providers_client_type_check CHECK (client_type IN (
+  'openai-responses',
+  'openai-completions',
+  'anthropic-messages',
+  'google-generative-ai',
+  'openai-codex',
+  'github-copilot',
+  'edge-speech',
+  'openai-speech',
+  'openai-transcription',
+  'openrouter-speech',
+  'openrouter-transcription',
+  'elevenlabs-speech',
+  'elevenlabs-transcription',
+  'deepgram-speech',
+  'deepgram-transcription',
+  'minimax-speech',
+  'volcengine-speech',
+  'alibabacloud-speech',
+  'microsoft-speech',
+  'google-speech',
+  'google-transcription'
+));