feat: mock non-speech audio generation (ElevenLabs, fal.ai, Gemini)#140
Merged
feat: mock non-speech audio generation (ElevenLabs, fal.ai, Gemini)#140
Conversation
commit: |
jpr5
force-pushed
the
blitz/audio-gen-118/integration
branch
from
70ace03 to
0fe22fb
Compare
Contributor
|
Just created tests with this for the elevenlabs adapter. It's looking good! |
Contributor
Author
|
@tombeckenham final answer? |
jpr5
added a commit
that referenced
this pull request
May 4, 2026
jpr5
force-pushed
the
blitz/audio-gen-118/integration
branch
from
e8ad015 to
60ec694
Compare
New handlers for ElevenLabs sound effects/music and fal.ai queue-based
audio. Gemini HTTP and WebSocket audio via inlineData parts. AudioResponse
broadened to support base64 string and {b64Json, contentType} object.
Convenience methods: onAudio(), onSoundEffect(), onMusic(), onFalAudio().
Router endpoint filtering for audio-gen and fal-audio types. Closes #118.
6 new test files covering ElevenLabs, fal.ai, Gemini HTTP/WS audio, recording, and multimedia type broadening. Non-speech audio rule added to competitive matrix test. 36+ new tests.
MCP server docs page. Non-speech audio row added to competitive matrix (aimock-only capability). Provider count updated 12 to 13 (Gemini Interactions). Multimedia feature card updated. Auto-update script synced with providerGroups and FEATURE_RULES. Changelog for PR #140.
jpr5
force-pushed
the
blitz/audio-gen-118/integration
branch
from
60ec694 to
031e243
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Adds mock support for non-speech audio generation endpoints, closing #118:
/v1/sound-generation) and music (/v1/music/*) endpoints with support for generation, streaming, and composition plans/fal/queue/submit/*,/fal/queue/requests/*,/fal/run/*) with full lifecycle (submit → status → result → cancel)generateContent/streamGenerateContentwithinlineDataparts containing audio MIME typesonAudio(),onSoundEffect(),onMusic(),onFalAudio()audiofield now supports bothstring(base64) and{ b64Json, contentType }object formaudio-genandfal-audioendpoint typesFiles changed (23 files, +3159/-50)
elevenlabs-audio.ts,fal-audio.tsgemini.ts,ws-gemini-live.ts,speech.tsserver.ts,router.ts,types.ts,helpers.ts,recorder.ts,stream-collapse.ts,llmock.ts,index.ts,fixture-loader.tselevenlabs-audio.test.ts,fal-audio.test.ts,gemini-audio.test.ts,gemini-audio-record.test.ts,ws-gemini-live-audio.test.ts,multimedia-types.test.tsindex.html,mcp/index.html,sidebar.jsTest plan
tsc --noEmitcleanprettier --checkcleaneslintcleanCloses #118