[Inference] fal-ai: audio-to-audio fix + text-to-audio + NeMo ASR & PersonaPlex

[jetjodh]

Summary

Adds and fixes audio model support for the fal-ai inference provider.

1. Fix audio-to-audio for fal-ai audioToAudio() now resolves url/headers/signal via makeRequestOptions and forwards them to getResponse (mirroring imageSegmentation), so the fal queue task can poll for results instead of throwing "URL and headers are required for audio-to-audio task". Input data-URL MIME handling reuses FAL_AI_AUDIO_MIME_MAP (consistent with the ASR fix), so audio/wav/audio/webm/etc. aren't rejected by fal's data-URL decoder.

2. Add text-to-audio support. New queue-based FalAITextToAudioTask (handles both audio_file and audio result shapes), a textToAudio() task function (auto-exposed on InferenceClient via the tasks barrel), a widened TextToAudioTaskHelper.getResponse signature, and export of the (previously defined-but-unexported) text-to-audio inference types from @huggingface/tasks.

3. ASR: handle NeMo/nemotron output shape + timestamps. fal's nemotron ASR endpoint returns the transcript under output (with a partial flag), not text like whisper — so the existing helper would reject it. getResponse now parses both text and output, and normalizes timestamps from chunks (whisper) or segments to HF's AutomaticSpeechRecognitionOutput.chunks.

Testing

• New unit tests: fal-ai audio-to-audio, text-to-audio, and automatic-speech-recognition (text/output/chunks/segments parsing).
• Verified end-to-end against the live fal API: nemotron ASR (correct transcript) and PersonaPlex batch audio-to-audio (audio returned).
• tsc --noEmit, eslint, and the new vitest specs all pass.

---

Note

Medium Risk
Touches live inference request/response paths for fal queue audio and ASR parsing; behavior changes for audio-to-audio callers but scope is provider-specific with new tests.

Overview
Expands fal-ai audio support: fixes audio-to-audio so queue jobs get url, headers, and signal (via makeRequestOptions + provider preparePayloadAsync), adds queue-based text-to-audio, and hardens ASR parsing for NeMo-style { output } plus optional chunks / segments timestamps.

Shared buildFalAiAudioDataUrl centralizes MIME remapping for fal data URLs (ASR and audio-to-audio). The public textToAudio() task is wired through the tasks barrel; @huggingface/tasks now exports text-to-audio inference types. Provider helper interfaces gain AbortSignal on text-to-audio / audio-to-audio getResponse and preparePayloadAsync on audio-to-audio (including hf-inference).

Unit tests cover fal queue polling, payload mapping, and ASR response variants.

^{Reviewed by Cursor Bugbot for commit 6ad8df7. Bugbot is set up for automated code reviews on this repo. Configure here.}