Use this integration guide to check API contracts, model choices, routing, and output requirements across audio, image, and video providers. It documents provider-specific constraints and resume behavior so production requests use an explicit host and model.
API contracts and production routing for the October 23, 2026 provider refresh.
Run score Not tested
See how to installThis guide covers tools, endpoints, models, and operating details for several audio, image, and video providers. It collects migration information for Google and ElevenLabs, describes audio features from HeyGen and Mistral, and maps image and video models to supported providers and input requirements. You can compare API fields, output formats, and constraints to select a route for a task. It also explains how to save information for resuming jobs and avoid submitting duplicate generation requests.
Use it before running an audio, image, or video generation workflow when you need to choose a provider or model, check required inputs and output destinations, review a migrated API contract, or resume a pending job.
The guide covers a provider refresh dated October 23, 2026. Before production, check the current tool input schema and specify the tool, host, model, operation, and quoted cost. The guide says not to switch hosts or models automatically. Configured credentials do not establish account access, and current account pricing may be needed for an estimate.
This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.
AI checked the SKILL.md for operations that need care and for setup requirements. The score comes only from actually running the skill (hands-on test).
Not counted in the score. Rated by AI (OpenAI Codex) as of Oct 24, 2026. Treat it as a guide and read the original before installing.
Review the instructions the agent will receive before you install.
Read the tool's current input schema before use. Announce tool, host, exact model, operation and quoted cost before production. No automatic host/model fallback. Use explicit output paths under the production project. Account access is not established merely by having a credential configured. Most new prices require a fresh account quote; do not use expired promotions as permanent prices.
gemini_omni_video: direct Gemini Interactions API model is
gemini-omni-1.1-flash. Old preview retired October 22. Continue editing with
previous_interaction_id; do not substitute it inside a Veo request.veo_video: Google backend requires Vertex; fal retains its own contracts.
Gemini API Veo has retired. Select Omni explicitly for the replacement workflow.google_imagen: new default gemini-nano-banana-2.1; Imagen models require
Vertex. Native Gemini image models use generate_content, not Imagen predict.elevenlabs_tts: eleven_v4 uses HTTP Text to Dialogue with inputs and
settings. Keep each narration request <=2,000 characters. next_text maps to
future_text; context strings <=100 characters. Style/speed/speaker boost are
not dialogue settings. eleven_v4_turbo uses the dialogue WebSocket; this file
adapter does not support timestamps or continuity controls on Turbo. It waits
for global is_final, not the per-turn marker. The current official realtime
tutorial documents Turbo although the older WebSocket reference says v3-only.heygen_tts: model_id heygen-voice-1, heygen-voice-1-turbo, or
heygen-voice-1-turbo-free. Pass an ACTIVE native public/workspace voice ID;
operation=list_voices discovers native voices. Professional clones only work
with the non-Turbo model. voice_type can prevalidate the category; the service
validates actual ownership/status. Completed speech and SSE both write WAV.
SSE parts are individual WAV containers, decoded before assembly. Timestamps
become an alignment sidecar and word_timestamps. Free access ends November 30,
2026; failures never switch to paid. Rate rejection retries are bounded and honor
short Retry-After delays; larger delays surface to the caller.heygen_catalog_tts: separate catalog IDs, /v3/voices/speech; explicitly choose
engine (starfish, heygen_voice, elevenlabs). Native professional clone IDs do
not belong here. Catalog output can be MP3 or WAV. Supply either suffix; the returned artifact
path uses the actual response codec suffix and preserves the audio.heygen_voice_convert: ACTIVE instant workspace voice only, at most300 seconds.
Exactly one audio_path (<=16 MB), audio_url or asset_id. Output WAV. Supply a
stable idempotency_key if resuming after an ambiguous timeout; no automatic retry.grok_tts: xAI narration /v1/tts, not Grok Voice realtime. language=auto by
default, voice_id defaults to eve; list_voices discovers voices. output_format
is an object, e.g. {"codec":"wav","sample_rate":24000}; this file adapter exposes
MP3/WAV, not headerless telephony codecs. Optional character alignment is saved.mistral_tts: model_id voxtral-mini-tts-3-0; exactly one voice_id or local
reference_audio_path. mp3/wav/flac/opus. Inline emotion/pace tags and expressiveness;
free-form style instructions are not available at launch. No realtime TTS claim.mai_tts: Azure Speech key/region, model_id MAI-Voice-2.1 or MAI-Voice-2.1-Flash.
voice_id is a managed voice base such as en-US-Harper (the model suffix is added).
The TTS selector translates speed and pitch through the Azure SSML adapter.
This adapter does not provision personal voice clones or grant gated access.mistral_stt: Voxtral Mini/Small Transcribe3, local audio files; timestamps are
segments, not words. Diarization implies segment timestamps. Raw transcript JSON
is persisted, including speaker and usage metadata.elevenlabs_soundtrack: video_paths (<=10, combined <=200 MB / 600seconds),
optional description/tags, add_sfx/use_audio_as_reference/separate_tracks. Separate
tracks return playable files in a sibling *_tracks directory; never treat a ZIP
as an audio file. The adapter rejects unsafe archive paths and oversized archives.| Model | Explicit tools / hosts |
|---|---|
| Nano Banana2.1 | google_imagen, gemini_fal_image, gemini_replicate_image |
| FLUX3 Image | bfl_image, flux3_fal_image, flux3_replicate_image |
| FLUX3 Max video | flux3_video (fal) |
| Vidu Q4 | vidu_video (fal), image_to_video or reference_to_video; no text-only route |
| Fibo2 | bria_image direct or bria_fal_image |
| MAI Image2.6 / Flash | mai_image, deployed Foundry models |
| Grok Imagine1.5 / Lite | grok_video direct xAI |
fal and Replicate have checked-in endpoint schemas under tools/provider_contracts. Pass provider_params only when documented by that host. Do not copy fal fields to Replicate or direct APIs. Existing Pro image model defaults remain unchanged on aggregators; select the new model explicitly.
BFL bounding-box layouts are encoded in the prompt per BFL docs, not a fabricated
boxes endpoint field. BFL supports up to10 reference images; width/height must be
provided together. Its API reference is authoritative over older narrative examples.
Bria persists structured metadata for later editing. Its shared endpoint can route
some legacy combinations to older Fibo models; the direct tool rejects those
combinations when advertising Fibo2. MAI requires model identity to match the
configured deployment; PNG output and <=2,359,296 pixels with each side >=768.
Grok1.5 references are limited to720p. Lite has no reference audio, reference images, last_frame or keyframes. Full1.5 supports preset voice references; custom audio references remain partner gated. Mid-video pins must be inside duration and occupy different1/3-second slots. No model substitution on failure. fal/Replicate/BFL/Grok jobs expose resume metadata; save job_path before polling and resume pending jobs instead of submitting duplicate paid generations.
realtime_audio is a bounded one-response file runner for Grok Voice3,
Eleven Realtime Mini/Max and MAI-Transcribe-2-Streaming. Input is text or mono PCM16
WAV (16/24kHz; Eleven requires24kHz). Voice output is WAV; MAI output is event JSON.
Input sending and event receiving run concurrently. MAI commits explicitly and
waits for final transcription, not a commit acknowledgment. Eleven uses ephemeral
session credentials and bursty input pacing for recorded files.
For live audio, VAD, interruptions, multiple turns, or function calls, use the
context-managed tools.audio._realtime_session.RealtimeAudioSession transport:
append_audio, commit, receive, request_response, cancel, and
submit_tool_result. The caller owns the session lifecycle and tool approvals.
Received tool calls are never executed automatically. The finite file runner
rejects tools because it cannot continue them after closing the socket. No microphone
UI, browser app, or voice-agent orchestration is implied by this transport layer.
Secrets remain in memory. No realtime translation or Kling4 support was added.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Create 3D objects from text or images, choose catalog assets for repeated scenery, and inspect the results in Blender. The workflow checks geometry, materials, scale, and ground contact while recording asset sources and generation costs.
Generate background music and songs with lyrics using ACE-Step 1.5, with controls for duration, tempo, and musical key. You can also restyle reference audio and separate vocals or individual instruments from mixed tracks.
Build voice assistants and conversational characters with ElevenLabs. Configure voices, language models, and external tools, then connect conversations to a website widget or use Twilio integration for outbound phone calls.
Create AI video clips from text or reference images, choosing among providers to match the task and budget. Supports vertical social videos, product photo animation, and conversational editing of existing clips with Gemini Omni Flash.
Generate video clips from text descriptions or reference images through multiple API services. Compare available providers by cost and task needs, choose aspect ratios, track generation progress, and refine existing clips through conversational editing with Gemini Omni.
Generate and edit images and videos through Atlas Cloud using one API key across multiple model families. Choose supported models for each task, download the results, and retain details about the model, inputs, and estimated cost.