Open
Conversation
…o, Mistral, Murf, Unreal Speech, Resemble) - Cartesia: sonic-3/sonic-2 with emotion-to-SSML mapping - Deepgram: aura-2 with static voice list and streaming - Hume: octave-2/octave-1 with version mapping and streaming - xAI: grok-tts with native audio tag passthrough - Fish Audio: s2-pro with model-as-header pattern - Mistral: voxtral-mini-tts-2603 with SSE streaming - Murf: GEN2/FALCON with dual model endpoints - Unreal Speech: two-step URI + direct streaming - Resemble: base64 JSON + direct streaming - ElevenLabs: added v3 audio tag processing - 166 new tests across 12 test files - All engines registered in factory, types, and exports
- Add engine table entries for Cartesia, Deepgram, Hume, xAI, Fish Audio, Mistral, Murf, Unreal Speech, Resemble - Add engine-specific examples with usage notes - Update timing table, SSML table, and Speech Markdown table - Update factory pattern engine list - Move Mistral/Murf/Unreal/Resemble to Completed in BACKLOG
- Replace Buffer.from() in ElevenLabs with cross-env base64ToUint8Array - Replace atob() in Mistral/Murf/Resemble with shared utility - Add shared src/utils/base64-utils.ts for cross-env base64 decoding - Fix Fish Audio checkCredentials to use GET /v1/model (no quota consumed) - Fix Resemble checkCredentials to use GET /v2/voices (no quota consumed) - Add voice discovery: Hume (16 static voices), Mistral (27 static voices) - Add Resemble voice listing via API - Fix xAI: remove dead processAudioTags no-op code - Fix pre-existing lint issues in google.ts, polly.ts, playht.ts, openai.ts, sherpaonnx.ts, abstract-tts.ts, azure.ts
- Add shared language-utils.ts with toIso639_3(), toLanguageDisplay() - Fix bcp47: use full BCP-47 codes (en-US not en) in static voice lists - Fix iso639_3: use proper 3-letter ISO 639-3 codes (eng not en) - Fix display: use human-readable names (English (US) not en-US) - Applies to: cartesia, deepgram, hume, xai, fishaudio, mistral, murf, unrealspeech, resemble
- Add ModelFeature type: streaming, audio-tags, inline-voice-cloning, open-source, word-boundary-events, character-boundary-events, ssml - Add FEATURES constants and ModelInfo interface to types.ts - Add getModels(), hasFeature(), _getCurrentModelId() to AbstractTTSClient - Define accurate _models metadata for all 23 engines based on code audit: - Real word boundaries: elevenlabs, google (beta), polly, azure, watson, sherpaonnx - Character boundaries: elevenlabs (all models) - Native SSML: google, polly, azure, watson, witai, sapi - Audio tags: elevenlabs v3, openai gpt-4o-mini-tts, cartesia sonic-3, xai grok-tts, fish audio s2-pro - Voice cloning: elevenlabs v3, cartesia sonic-3, hume octave-2, fish audio s2-pro, mistral, resemble - Open source: sherpaonnx, sherpaonnx-wasm, espeak-ng, mistral, resemble
- Pipe response.body directly when not using timestamps (avoids buffering) - Only buffer when useTimestamps=true (needs JSON response for alignment) - Only buffer when format=wav (needs mp3-to-wav conversion) - Add streaming feature to all ElevenLabs models - Update BACKLOG: mark streaming improvements as done for Cartesia, Deepgram, ElevenLabs, Polly; note Google Cloud TTS SDK limitation
4 tasks
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.