Which API should I use? - Modulate

Modulate’s models are grouped into families by the kind of output they produce. Within a family, endpoints differ by language coverage, latency, and whether they take a file or a live stream. Each capability page below carries the full parameter, response, and audio format detail for its endpoints.

Model families

Family	Model	Output
Transcription	Multilingual Transcription	A transcript with per-utterance timing, speaker labels, and optional emotion, accent, deepfake, and PII/PHI signals. Batch and streaming.
	English Fast Transcription	An English transcript, with speaker turns when diarization is enabled. Batch and streaming.
	Multilingual Fast Transcription	A transcript, its duration, and its language. No metadata. Batch and streaming, though only batch reports the language.
Detection	Deepfake Detection	A `synthetic`, `non-synthetic`, or `no-content` verdict per frame, with confidence. Batch and streaming.
	Emotion Detection	A whole-file emotion label plus a per-window time series. Batch.
	Accent Detection	A whole-file accent label plus a per-window time series. Batch.
	Music & Speech Detection	Music and speech probabilities per 192 ms frame, plus clip totals. Batch and streaming.
	AI Music Detection	A clip verdict on AI-generated music, plus per-window vocal and instrumental scores. Batch and streaming.
	Language Detection	The spoken language with a confidence score, across 100 languages. Batch.
	Audio Event Detection	A probability for each non-speech sound event detected, from a vocabulary of 42. Batch.
Redaction	PII/PHI Redaction	A redacted transcript plus audio with the sensitive ranges silenced. Batch and streaming.
Triage	Velma Triage	Behaviors, conversation type, participant roles, topics, sentiment, a summary, and a diarized transcript. Batch and streaming.

No Detection model returns a transcript.

Endpoints that overlap

Three models return a transcript

Multilingual Transcription, PII/PHI Redaction, and Velma Triage all return a transcript. Pairing any of the last two with a transcription call returns the same text twice.

Requirement	Endpoint that covers it
A redacted transcript and audio with the sensitive ranges silenced	PII/PHI Redaction. A separate transcription call returns the same text.
Behaviors, topics, and sentiment across a conversation	Velma Triage. The diarized transcript comes back as `clips`.

Four signals have two paths

Each is available as a flag on Multilingual Transcription, attached per utterance, or as a dedicated endpoint that produces no transcript. English Fast and Multilingual Fast Transcription carry none of them.

Signal	Multilingual Transcription flag	Dedicated endpoint	What the dedicated endpoint adds
Deepfake	`deepfake_signal=true`, one score per utterance	Deepfake Detection	Frame-level verdicts, explicit `no-content` for silence, and verdicts on live audio without a transcript
Emotion	`emotion_signal=true`, one label per utterance	Emotion Detection	A whole-file label and a per-window time series, without a transcript
Accent	`accent_signal=true`, one label per utterance	Accent Detection	A whole-file label and a per-window time series, without a transcript
PII/PHI	`pii_phi_tagging=true`, spans tagged in the transcript text	PII/PHI Redaction	Silenced audio, not only tagged text

Common scenarios

Goal	Endpoint
Recorded English calls, high volume	English Fast Transcription (batch). Bound parallel requests with a semaphore to stay inside the concurrency cap.
Recorded calls in mixed or non-English languages, transcript only	Multilingual Fast Transcription (batch). Pass `language` when it is known.
Live non-English captions, minimum latency	Multilingual Fast Transcription (streaming), for the 25 European languages it covers. The language is identified automatically and is not reported, so pair it with Language Detection if the code is needed. Outside those 25, use Multilingual Transcription (streaming).
Captions, or search that seeks into the audio	English Fast Transcription (batch) with `time_stamps=true`. Returns a start time, end time, and alignment confidence per word, in seconds from the start of the file.
Meeting transcription with speakers and emotion	Multilingual Transcription (batch) with `speaker_diarization=true` and `emotion_signal=true`.
Live captions with speaker labels or non-English audio	Multilingual Transcription (streaming).
Voice agent input, minimum latency	English Fast Transcription (streaming) with `endpointing=true`. Replace the displayed partial on each message rather than appending.
Live English captions that attribute turns to speakers	English Fast Transcription (streaming) with `diarize=true` and `endpointing=true`. Check `speakers_capped` before trusting the labels past ten speakers.
Screening a submitted clip for AI-generated voice	Deepfake Detection (batch).
Anti-spoofing during a live voice-authentication flow	Deepfake Detection (streaming). Frame verdicts arrive during the call.
A compliance recording that must be shareable	PII/PHI Redaction (batch). Returns the silenced MP3 and the tagged transcript together.
Routing audio by spoken language	Language Detection (batch). Read `predicted_language_code`; low `confidence` means no commitment.
Processing only speech from a live stream	Music & Speech Detection (streaming). Route on the frame classification.
Screening uploaded tracks for AI-generated music	AI Music Detection (batch). The clip `primary_verdict` is more accurate than the per-window scores.
Identifying non-speech sounds in a clip	Audio Event Detection (batch). Entries are independent probabilities, so threshold each event you care about; an absent key means not confidently detected, not absent from the audio.
Fraud or compliance review on recorded calls	Velma Triage (batch) with a detection package.
Live monitoring for escalation or churn	Velma Triage (streaming). `behavior_detection` events arrive during the call.