Upload Audio

A descriptive title for your audio (e.g., 'Customer Call' or 'Team Meeting').

Optional notes about the audio content or context.

URL to your audio/video source (YouTube, Instagram, Twitter, Facebook, Dropbox, or any direct media link). Audio will be extracted if source is video. Leave empty if uploading a file instead.

Start point in milliseconds to begin analysis. Use 0 to start from the beginning. If provided (>0), end_millis is required with minimum 1-second (1000ms) gap.

End point in milliseconds to stop analysis. Use 0 only when analyzing the full audio (start_millis must also be 0). If start_millis is provided, end_millis is required and must be at least 1000ms greater than start_millis.

Your webhook URL to receive a notification when analysis completes. Must be an https URL on a publicly reachable host.

Upload an audio file directly (mp3, wav, aac, m4a). File upload takes priority over media_url.

Speaker diarization. Enabled by default. Disabling this stage reduces the per-second credit cost.

Text emotion analysis. Enabled by default. Requires a transcript: ignored (forced off) when transcription is disabled and you supply no transcript. Supplying a transcript is the exception — the words already exist, so this is honoured as you sent it. Disabling this stage reduces the per-second credit cost.

Transcript / ASR generation. Enabled by default. When disabled, no transcript is produced and text_emotion is forced off. Supplying a transcript overrides this field entirely: our ASR is skipped either way, but your transcript is used and text_emotion still applies. Disabling this stage reduces the per-second credit cost.

Language code for analysis. Auto-detected if not provided. With expected_languages it must be one of them.

Opt in to mixed-language transcription: the speech may switch language, and each stretch is transcribed in the language it is spoken in. Once the audio completes, the lines that are not in its main language are also translated into the main language and billed as a translation, on top of transcription (auto_translation reports it). This is input only; the languages actually detected are reported separately.

Comma-separated codes of the languages the audio may contain, the main one included (e.g. en,ja), 1 to 5 after duplicates are removed. Case and whitespace are ignored, a region is dropped (pt-BR is pt) and an alias maps to the Whisper spelling (iw is he); Cantonese is yue. Language detection is restricted to the set, with or without multilingual. If language is also sent it must be one of them (422 invalid_language otherwise). If language is omitted, detection still runs, restricted to the set. An unknown code, or more than 5, is refused with 422 invalid_language before anything is charged.

Optional: a transcript you already have for this audio. When supplied we skip our own speech-to-text, use your transcript's speaker turns as the diarization, and name the speakers from it — so results come back with real participant names. Supplying one overrides transcription: our ASR is skipped either way, and you are charged less because that stage is not billed. A start_millis/end_millis trim is rejected: timestamps would not line up with the trimmed audio. A media_url source is accepted — we download it first, then apply your transcript once processing completes. That apply then delivers callback_url (success or failure). An uploaded file has no download wait: it applies in the same request and its callback fires normally.

Format of transcript. 'auto' (the default) detects it. Supported: 'auto', 'text', 'tldv_json', 'teams_vtt', 'zoom_vtt', 'vtt', 'srt'. Works with tl;dv, Zoom, Microsoft Teams, Otter, Fathom, Tactiq and most .vtt/.srt exports. Google Meet's own transcript is not supported yet — it timestamps only every 5 minutes, which cannot be aligned to the audio.

Milliseconds added to every timestamp in transcript to place it on the media timeline. Positive means the transcript starts later than the recording (transcription began after record). Negative means it starts earlier (transcription running before record). 0 (the default) is today's behaviour. A negative offset that places any turn before 0 ms is rejected. Ignored when no transcript is supplied.

Declared recording type (not a file format). 'generic' (the default) is a generic recording: no stance pass. 'contact_center_call' marks a support/sales call so speaker roles and stance analysis can apply. Omit (or send empty) for generic. Unrecognised values — including the spelling 'contact_centre_call' — are rejected. A call uploaded as video starts generic; PUT the companion audio id after processing completes. POST /v1/audios does not accept audio_type — tag afterwards via PUT /v1/audios/{id}/audio-type.