Add Eden AI as a TTS provider - #310
Open
MVS-source wants to merge 1 commit into
Open
Conversation
Eden AI is a gateway that exposes many text to speech engines (OpenAI, Google, Amazon, Microsoft, ElevenLabs and more) behind one API and one key. This adds it as a new TTS backend, selected with tts_model=edenai. - New provider podcastfy/tts/providers/edenai.py - Registered in the TTS factory - Default edenai block in conversation_config.yaml - EDENAI_API_KEY loaded in Config - Docs updated (config and conversation_custom, plus the versioned docs) - Tests: mocked unit tests plus a skipped end to end test, matching the other paid providers
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What this adds
This adds Eden AI as a text to speech backend, selectable with
tts_model=edenai.Eden AI is a gateway that routes to many TTS engines (OpenAI, Google, Amazon, Microsoft, ElevenLabs and more) behind a single API and one key. So one integration gives Podcastfy users a range of voices and engines without adding a dependency per vendor. The engine is chosen with the
text_to_speech.edenai.modelconfig value, and the list stays open as Eden AI adds engines. Infrastructure is in the EU and prompts and outputs are not stored by default, which some users care about.Changes
podcastfy/tts/providers/edenai.py, mirroring the existing provider structureedenaiinTTSProviderFactoryedenaiblock inconversation_config.yaml(MALE and FEMALE voices work across every engine)EDENAI_API_KEYloaded inConfigusage/config.md,usage/conversation_custom.md, the README and the versioneddocs/sourcecopiesTesting
Verified end to end against the live Eden AI API with a real key: generated audio for the openai and google engines, with both MALE and FEMALE options and a specific voice id, and confirmed valid MP3 output. The mocked unit tests pass under pytest. No new dependency (uses
requests, already required).Notes
Voices of "MALE" or "FEMALE" work on every engine. You can also set a specific engine voice id (for example "alloy" for the openai engine, or "en-US-Standard-A" for the google engine).