API REFERENCE

Audio

Text-to-speech, speech-to-text, music, sound effects, voice changing, dubbing and voice cloning — one API key, every provider.

A single audio surface covers text-to-speech, transcription, music, sound effects, dubbing, voice changing and voice cloning. The core endpoints are OpenAI-compatible, while richer extras — voice settings, speaker diarization, dubbing — are accepted wherever the upstream provider supports them.

List the available voices first; cloned voices you create show up in the same list and are used the same way.

Endpoints in this section: /v1/audio/speech, /music, /sound-effects, /transcriptions, /audio-isolation, /voice-changer, /dubbing, /voices, plus /v1/voices/* for cloning.

Text-to-speech

Synthesise speech from text. Returns raw audio bytes with the matching Content-Type (e.g. audio/mpeg). PCM and µ-law formats include a WAV header so they play in any browser.

POSThttps://api.airforce/v1/audio/speech

TTS models

…· live

Parameter	Type	Required	Description
model	string	Required	TTS model ID. See /v1/models for IDs with input_modalities containing "text" and output_modalities containing "audio".
input	string	Required	Text to synthesise. Long inputs are chunked automatically.
voice	string	Required	Voice ID. Use GET /v1/audio/voices to list options. Cloned voices appear here too.
response_format	string	Optional	"mp3" (default), "mp3_44100_128", "mp3_44100_192", "pcm_22050", "pcm_24000", "pcm_44100", "ulaw_8000".
speed	float	Optional	0.25 – 4.0. OpenAI-compatible. Some upstream providers ignore this.
voice_settings	object	Optional	ElevenLabs-shape: { stability: 0–1, similarity_boost: 0–1, style: 0–1, use_speaker_boost: bool }.
language_code	string	Optional	ISO-639-1 hint, e.g. "de", "en", "ja". Improves prosody for multilingual models.
seed	integer	Optional	Reproducibility seed where supported.

Example

curl https://api.airforce/v1/audio/speech \
  -H "Authorization: Bearer sk-air-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  --output speech.mp3 \
  -d '{
    "model": "elevenlabs-multilingual-v2",
    "input": "Willkommen bei Airforce.",
    "voice": "21m00Tcm4TlvDq8ikWAM",
    "response_format": "mp3_44100_128",
    "voice_settings": {"stability": 0.6, "similarity_boost": 0.8}
  }'

List voices

Returns every voice you can pass as the "voice" parameter on TTS / voice-over / audiobook calls. Cloned voices are returned here too once their status is active.

GEThttps://api.airforce/v1/audio/voices

curl https://api.airforce/v1/audio/voices \
  -H "Authorization: Bearer sk-air-YOUR_API_KEY"

Response shape

Parameter	Type	Required	Description
voices[]	array	Optional	List of voice descriptors.
voices[].voice_id	string	Optional	Provider-native voice identifier — the field is voice_id (not id). Pass this value as "voice".
voices[].name	string	Optional	Human-readable name.
voices[].description	string	Optional	Short description, when the upstream exposes one.
voices[].category	string	Optional	"premade" \| "cloned" \| "professional".
voices[].preview_url	string	Optional	Short audio sample, when the upstream exposes one.
voices[].labels	object	Optional	Free-form metadata: gender, language, accent, age, use case.
live	boolean	Optional	true when the catalog came from a live upstream call; false when served from the built-in premade fallback.

{
  "voices": [
    {
      "voice_id": "CwhRBWXzGAHq8TQ4Fs17",
      "name": "Roger - Laid-Back, Casual, Resonant",
      "description": "Easy going and perfect for casual conversations.",
      "preview_url": "https://.../58ee3ff5.mp3",
      "category": "premade",
      "labels": {"accent": "american", "gender": "male", "language": "en", "use_case": "conversational"}
    }
  ],
  "live": true
}

Music generation

Generate full music tracks from a text prompt. Returns binary audio.

POSThttps://api.airforce/v1/audio/music

This endpoint serves the native music models (e.g. music-v1). Suno models (suno-*) are not available here and return provider_not_supported — call them via the /v1/images/generations endpoint instead (see the Media reference).

Parameter	Type	Required	Description
model	string	Required	Music model ID, e.g. "music-v1".
prompt	string	Required	Style / mood / structure description.
duration_seconds	integer	Optional	Track length. Range depends on the model (typically 15–120 s).
response_format	string	Optional	"mp3" (default) or provider-native.
instrumental	boolean	Optional	When true, suppresses vocals.
style	string	Optional	Optional genre tag list, e.g. "EDM, bass, dark".

curl https://api.airforce/v1/audio/music \
  -H "Authorization: Bearer sk-air-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  --output track.mp3 \
  -d '{
    "model": "music-v1",
    "prompt": "Lofi hip-hop beat with soft piano and rain",
    "duration_seconds": 60,
    "instrumental": true
  }'

Sound effects

Short SFX from a text prompt. Same shape as music, just shorter durations.

POSThttps://api.airforce/v1/audio/sound-effects

Parameter	Type	Required	Description
model	string	Required	SFX model ID.
prompt	string	Required	Effect description, e.g. "thunder rumble fading into rain".
duration_seconds	integer	Optional	Length, typically 0.5–22 s.
response_format	string	Optional	"mp3" (default).

curl https://api.airforce/v1/audio/sound-effects \
  -H "Authorization: Bearer sk-air-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  --output thunder.mp3 \
  -d '{
    "model": "sfx-v1",
    "prompt": "Distant thunder rolling, then rain",
    "duration_seconds": 8
  }'

Transcriptions (speech-to-text)

Multipart upload of an audio file. Returns the transcribed text.

POSThttps://api.airforce/v1/audio/transcriptions

Transcription models

…· live

Parameter	Type	Required	Description
model	string	Required	Transcription model ID. See the live list below for valid IDs.
file	binary	Required	Audio file. Supports mp3, wav, m4a, flac, ogg, webm.
language_code	string	Optional	ISO-639-1 language hint (also accepted as "language"). Auto-detected when omitted.
diarize	boolean	Optional	Separate speakers. When true, each word carries a speaker_id.
num_speakers	integer	Optional	Expected speaker count, used together with diarize.
tag_audio_events	boolean	Optional	Mark non-speech events (laughter, silence, music) in the output.
timestamps_granularity	string	Optional	"word" (default) or "character".
additional_formats	string	Optional	Request extra rendered outputs (e.g. srt / vtt) alongside the JSON.

curl https://api.airforce/v1/audio/transcriptions \
  -H "Authorization: Bearer sk-air-YOUR_API_KEY" \
  -F "[email protected]" \
  -F "model=elevenlabs-scribe" \
  -F "language_code=de" \
  -F "diarize=true"

Response shape

{
  "language_code": "deu",
  "language_probability": 0.98,
  "text": "Willkommen zum Meeting...",
  "words": [
    {"text": "Willkommen", "start": 0.0, "end": 0.62, "type": "word", "logprob": -0.08, "speaker_id": "speaker_0"},
    {"text": " ", "start": 0.62, "end": 0.62, "type": "spacing", "logprob": 0.0}
  ],
  "audio_duration_secs": 412.5,
  "transcription_id": "tx_01HXY..."
}

The response follows the upstream provider’s native shape (ElevenLabs Scribe), not OpenAI Whisper’s: tokens come back as a flat words[] array (each with a type of word/spacing and a logprob), not segments[]. Duration is audio_duration_secs, and language_code is ISO-639-3 (e.g. eng, deu). Per-word speaker_id is only present when you pass diarize=true.

Audio isolation

Strip background noise from a clip while preserving the foreground voice. Multipart upload, returns audio.

POSThttps://api.airforce/v1/audio/audio-isolation

Parameter	Type	Required	Description
model	string	Required	Isolation model ID.
file	binary	Required	Input audio.

curl https://api.airforce/v1/audio/audio-isolation \
  -H "Authorization: Bearer sk-air-YOUR_API_KEY" \
  -F "model=isolation-v1" \
  -F "[email protected]" \
  --output clean.mp3

Voice changer (speech-to-speech)

Take input speech and re-render it in a different voice while preserving timing and inflection.

POSThttps://api.airforce/v1/audio/voice-changer

Parameter	Type	Required	Description
model	string	Required	Voice-change model ID.
voice	string	Required	Target voice ID. Same catalog as TTS.
file	binary	Required	Input audio.
voice_settings	object	Optional	Optional ElevenLabs-shape settings (stability, similarity_boost, …).

curl https://api.airforce/v1/audio/voice-changer \
  -H "Authorization: Bearer sk-air-YOUR_API_KEY" \
  -F "model=voice-changer-v1" \
  -F "voice=21m00Tcm4TlvDq8ikWAM" \
  -F "[email protected]" \
  --output transformed.mp3

Dubbing

Async dubbing into one target language. Returns a dubbing_id immediately; poll until the status reads "dubbed", then download the dubbed audio for that language.

1. Create job

POSThttps://api.airforce/v1/audio/dubbing

Parameter	Type	Required	Description
model	string	Required	Dubbing model ID.
file	binary	Required	Source audio or video (mp3, wav, m4a, mp4 — audio is extracted automatically). Alternatively pass source_url.
target_lang	string	Required	Target language code (ISO-639-1). One language per job — repeating the field does not add languages.
source_lang	string	Optional	Source language. "auto" or omit for auto-detect.
num_speakers	integer	Optional	Hint for diarization. Auto when omitted.
drop_background_audio	boolean	Optional	Remove background music / noise from the dub.
watermark	boolean	Optional	Add an audible watermark to the output.

curl https://api.airforce/v1/audio/dubbing \
  -H "Authorization: Bearer sk-air-YOUR_API_KEY" \
  -F "model=dubbing-v1" \
  -F "[email protected]" \
  -F "target_lang=de" \
  -F "source_lang=en"

{
  "dubbing_id": "abc123def456",
  "expected_duration_sec": 42.5
}

2. Poll status

GEThttps://api.airforce/v1/audio/dubbing/:dubbing_id

Status is forwarded from the provider verbatim. status reads "dubbing" while it runs and "dubbed" when ready (not "completed"). Languages are under target_languages (not available_languages), and there is no progress field.

{
  "dubbing_id": "abc123def456",
  "status": "dubbed",
  "source_language": "en",
  "target_languages": ["de"],
  "media_metadata": {"duration": 42.5, "content_type": "video/mp4"},
  "name": "english.mp4",
  "created_at": "2026-05-06T22:30:00Z",
  "editable": false,
  "error": null
}

3. Download per language

GEThttps://api.airforce/v1/audio/dubbing/:dubbing_id/audio/:lang

curl https://api.airforce/v1/audio/dubbing/abc123def456/audio/de \
  -H "Authorization: Bearer sk-air-YOUR_API_KEY" \
  --output german.mp3

Voice cloning

Clone a voice from short audio samples and reuse it across every speech endpoint. Voice cloning requires explicit consent — fetch the current consent text, hash it, and submit the hash with your samples.

1. Fetch consent text

GEThttps://api.airforce/v1/voices/consent-text

{
  "text": "I confirm that the voice samples I am uploading are either my own voice or a voice I have explicit permission to clone…",
  "hash": "9f4b0c8d2e…"
}

2. Create the clone

POSThttps://api.airforce/v1/voices/clone

Parameter	Type	Required	Description
name	string	Required	Public voice name shown in the library.
description	string	Optional	Optional free-text description.
consent_hash	string	Required	SHA-256 of the consent paragraph. Fetch the current text via GET /v1/voices/consent-text and pass its hash field.
files	binary	Required	1–25 audio samples. Repeat the form field per file. Total ≤ 200 MB. 30 s – 3 min per clip works best.

curl https://api.airforce/v1/voices/clone \
  -H "Authorization: Bearer sk-air-YOUR_API_KEY" \
  -F "name=My voice" \
  -F "description=Calm, conversational" \
  -F "consent_hash=9f4b0c8d2e..." \
  -F "[email protected]" \
  -F "[email protected]"

{
  "voice_id": "voice_01HXY...",
  "name": "My voice",
  "status": "active",
  "created_at": "2026-05-06T22:30:00Z"
}

Heads-up on field names: the create response returns the new voice as voice_id, whereas GET /v1/voices/library lists clones under provider_voice_id. Both hold the same identifier — the value you pass as voice.

3. List your library

GEThttps://api.airforce/v1/voices/library

curl https://api.airforce/v1/voices/library \
  -H "Authorization: Bearer sk-air-YOUR_API_KEY"

Parameter	Type	Required	Description
voices[].provider_voice_id	string	Optional	Pass as "voice" on TTS / voice-changer endpoints.
voices[].status	string	Optional	"active" \| "errored" \| "deleting".
voices[].provider	string	Optional	Upstream that hosts the clone.
voices[].last_error	string	Optional	Set when status is "errored".

4. Update / delete

PATCHhttps://api.airforce/v1/voices/clone/:id

DELETEhttps://api.airforce/v1/voices/clone/:id

PATCH accepts name and description in a JSON body. DELETE removes the voice both locally and at the upstream provider.

Notes

Audio responses are returned as raw bytes with the right Content-Type. PCM / µ-law formats are wrapped in a minimal WAV header so they’re browser-playable as-is.
Multipart endpoints (transcriptions, isolation, voice-changer, dubbing, cloning) accept up to 200 MB per request.
Voice IDs work across providers: a cloned ElevenLabs voice can be passed straight to /v1/audio/voice-changer.
Cost is metered per character (TTS), per second (music / SFX / dubbing / voice-changer) or per audio minute (transcription) and is deducted from your balance. Audio endpoints do not send an X-Cost-Cents response header — track spend in your dashboard usage log.