RESOURCES

Changelog

Changes to the API, newest first. Additive changes (new fields, events, languages) land without notice; anything breaking ships as a new version and is announced here first.

2026-09-04

The language set is 30

The supported set is 30 languages (Languages). New: Cantonese, Norwegian, Swedish, Danish, Catalan, Croatian, Serbian, Bulgarian, Slovak, Lithuanian, Latvian, Belarusian, and Kazakh, as source and target on uploads. Hindi, Turkish, Polish, Filipino, Tamil, Telugu, Bengali, and Czech are no longer offered as source or target; a request naming one returns 422 unsupported_language. Live sessions accept 11 of the 30 as source, and GET /v1/languages reflects the set.

2026-09-03

Live latency restated end to end

Live latency is now stated end to end: each language's dub runs 5–9 seconds behind the source -- translation 2–6 seconds depending on the quality setting, voice about 1 second, lip-sync about 2 seconds more (Latency). Transport stays ~50 ms with North American colocation. The earlier audio-only figure is withdrawn.

2026-08-26

API access is enterprise-only

API access is enterprise-only: keys are issued under Studio contracts (private integrations, volume pricing, a named point of contact) -- book a call to get set up. Live sessions deliver each speaker's translated voice on the original video.

2026-08-23

Live latency published; live_source on languages

Live latency is now documented (Latency; the figures were restated in the 2026-09-03 entry above). Live sessions accept a subset of the languages as source (the set was restated in the 2026-09-04 entry above); GET /v1/languages now returns a live_source flag per language (additive), and Live languages lists the set. Uploads keep every language as source.

2026-08-23

Audio-only dubs: dub_mode

POST /v1/dubs accepts dub_mode: "audio": the dub delivers the audio tracks only, metered at the contract's audio-only rate, and audio sources (podcasts, voice tracks) use this lane. "full" (video + lip-sync) stays the default. Create a dub documents the field.

2026-08-16

SRT in & out on live sessions

Live sessions now speak SRT (Secure Reliable Transport) on both legs: ingest.protocol: "srt" returns an srt_url + passphrase pair (AES on the link), and outputs with protocol: "srt"get each language's dubbed feed pushed to the srt_url you provide. Protocols still mix freely per session. SRT in & out has both legs.

2026-08-16

Audio tracks on every output

Every finished language now delivers its audio as standalone files: format=audio returns the full mix exactly as it sits in the mp4; format=voice returns the dubbed voice track alone, no scene bed, for your own mixing. Same signed-URL redirect as the video, covered by the same dub.output_ready webhook. Outputs & subtitles documents both.

2026-08-13

The Familiar API reference is public

The full /v1 reference is live on this site. Documented surface:

The API is enterprise-only: private access under a Studio contract, with volume pricing, raised limits, and a named point of contact for the integration. Book a call and your key is issued with the contract.