mirror of
https://github.com/heygen-com/hyperframes.git
synced 2026-09-07 18:26:17 +00:00
Miguel Ángel
0a66671fc5
* fix(media-use): tag HeyGen TTS generation with attribution header
Centralizes the X-HeyGen-Client-Source header into HEYGEN_CLIENT_SOURCE_ARGV
in heygen-cli.mjs and reuses it in heygen-search.mjs (dropping the duplicated
inline literal) so voice-provider's `voice speech create` call carries it too.
The generation call was previously untagged, making media-use TTS usage
invisible in HeyGen's billing/analytics warehouse; the read-only `voice list`
discovery call intentionally stays untagged.
* feat(media-use): add local LTX video generate provider
* feat(media-use): add HeyGen avatar-video generate provider
* feat(media-use): register video as a real provider type
* docs(media-use): document the wired video type and full HeyGen tagging coverage
resolve --type video is now the default path (HeyGen avatar video first,
local LTX fallback, sign-in nudge on auth failure) instead of a manual
recipe; correct the claim that only search requests are tagged now that
TTS and avatar-video generation carry the attribution header too.
* fix(media-use): wire --avatar-id/--voice-id CLI flags and close video-provider auth/cache gaps
- resolve.mjs never implemented the --avatar-id/--voice-id override that
operations.md documented, so following the docs crashed with
ERR_PARSE_ARGS_UNKNOWN_OPTION; wire the flags through to ctx.
- defaultAvatarId/defaultStarfishVoiceId cached a failed discovery lookup
as a permanent null, disabling heygen.video after one transient miss;
cache only a truthy id, matching the same fix in voice-provider.mjs's
defaultVoiceId.
- the avatar-video onboarding nudge only fired on a video-create failure,
never when avatar/voice discovery itself was unauthenticated (the
common unauthenticated case) -- propagate the discovery failure reason
so onboarding fires either way.
- dedupe the CLI-shelling JSON helper (heygen-cli.mjs's new runHeygenJson)
and the local-model argv-template builder (local-models.mjs's new
buildArgv) instead of leaving byte-identical copies in each provider.
* fix(media-use): address avatar-video PR review feedback
- heygenVideoGenerate short-circuits after the first discovery-call
failure instead of always attempting both avatar list and voice list,
so an unauthenticated caller gets one onboarding message and one
provider-error telemetry ping instead of a double-fire.
- runHeygenJson logs a diagnostic when a CLI call succeeds but returns
unparseable JSON, instead of silently returning null.
- dedupe the "avatar video is free" onboarding string into one constant
(was duplicated across three call sites).
* fix(media-use): match review-requested naming and message conventions
- export AVATAR_VIDEO_SIGNIN_MESSAGE from heygen-video-provider.mjs so
the test imports the canonical string instead of redeclaring it.
- runHeygenJson's non-JSON diagnostic now matches heygen-search.mjs's
existing wording ("returned non-JSON output").
58 lines
1.7 KiB
JavaScript
58 lines
1.7 KiB
JavaScript
import { HEYGEN_CLIENT_SOURCE_ARGV, runHeygenJson } from "./heygen-cli.mjs";
|
|
|
|
// Voice / TTS generation via the HeyGen CLI — the only external CLI media-use
|
|
// shells (CLI-only invariant: media-use holds no keys; the CLI owns auth).
|
|
// Flags verified against `heygen voice speech create --help` (v0.3.0).
|
|
|
|
function result(url, duration, provider, intent) {
|
|
if (!url) return null;
|
|
return {
|
|
url,
|
|
source: "generated",
|
|
metadata: {
|
|
description: intent,
|
|
provider,
|
|
...(duration != null && { duration }),
|
|
provenance: { prompt: intent },
|
|
},
|
|
};
|
|
}
|
|
|
|
// HeyGen TTS requires a starfish-engine voice. Default to the first one the
|
|
// catalog returns (deterministic order); pass ctx.voiceId to override.
|
|
// ponytail: listed once per process; the resolved asset is frozen + cached after
|
|
// first use, so the network list only happens on a cache miss. Cache only a
|
|
// truthy id -- a transient list failure must not poison the cache with `null`
|
|
// and permanently disable TTS for the rest of the process.
|
|
let cachedVoiceId;
|
|
function defaultVoiceId() {
|
|
if (cachedVoiceId) return cachedVoiceId;
|
|
const j = runHeygenJson(
|
|
"heygen",
|
|
["voice", "list", "--engine", "starfish", "--limit", "1"],
|
|
"voice list",
|
|
);
|
|
cachedVoiceId = j?.data?.[0]?.voice_id || null;
|
|
return cachedVoiceId;
|
|
}
|
|
|
|
export async function heygenTtsGenerate(intent, ctx) {
|
|
const voiceId = ctx?.voiceId || defaultVoiceId();
|
|
if (!voiceId) return null;
|
|
const p = runHeygenJson(
|
|
"heygen",
|
|
[
|
|
...HEYGEN_CLIENT_SOURCE_ARGV,
|
|
"voice",
|
|
"speech",
|
|
"create",
|
|
"--text",
|
|
intent,
|
|
"--voice-id",
|
|
voiceId,
|
|
],
|
|
"tts",
|
|
);
|
|
return result(p?.data?.audio_url, p?.data?.duration, "heygen.tts", intent);
|
|
}
|