Audio (speech · TTS & STT)

curl https://sovrgpt.com/api/v1/audio/speech \
  -H "Authorization: Bearer $SOVR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "supertonic-3",
    "input": "Guten Tag <breath> willkommen bei SovrGPT.",
    "voice": "F3",
    "response_format": "wav"
  }' --output hello.wav

Content-Type: audio/wav        (or audio/flac, audio/mpeg …)
X-Voice-Provider: supertonic   (or: cosyvoice / mistral)

# German with tags and emphasis
curl https://sovrgpt.com/api/v1/audio/speech \
  -H "Authorization: Bearer $SOVR_KEY" -H "Content-Type: application/json" \
  -d '{
    "provider": "cosyvoice",
    "voice": "de-thorsten",
    "input": "Und dann [breath] öffnete ich die Tür. [laughter] Das war <strong>unglaublich</strong>."
  }' --output tags.wav

curl https://sovrgpt.com/api/v1/audio/speech \
  -H "Authorization: Bearer $SOVR_KEY" -H "Content-Type: application/json" \
  -d '{
    "provider": "cosyvoice",
    "voice": "de-thorsten",
    "input": "Diese Zeiten sind für immer vorbei.",
    "emotion": "Sprich sehr traurig, leise und langsam."
  }' --output sad.wav

REF=$(base64 -w0 my_voice.wav)
curl https://sovrgpt.com/api/v1/audio/speech \
  -H "Authorization: Bearer $SOVR_KEY" -H "Content-Type: application/json" \
  -d "{
    \"provider\": \"cosyvoice\",
    \"input\": \"A new sentence, spoken in my cloned voice.\",
    \"reference_audio_b64\": \"$REF\",
    \"prompt_text\": \"<verbatim transcript of the reference clip>\"
  }" --output cloned.wav

curl https://sovrgpt.com/api/v1/audio/transcriptions \
  -H "Authorization: Bearer $SOVR_KEY" \
  -F file=@recording.webm \
  -F language=de \
  -F response_format=json

# 1. Fetch a ticket — same key, same `transcribe` scope
curl -s -X POST https://sovrgpt.com/api/v1/audio/uploads \
  -H "Authorization: Bearer $SOVR_KEY" \
  -H "content-type: application/json" \
  -d '{"mime":"audio/ogg","size":18234012}'

{
  "upload_id": "0f1c…",
  "upload_url": "https://…/storage/v1/object/upload/sign/api-audio/…",
  "token": "…",
  "content_type": "audio/ogg",
  "max_bytes": 104857600
}

# 2. Upload the bytes directly — NOT to us
curl -s -X PUT "$upload_url" \
  -H "content-type: audio/ogg" \
  --data-binary @recording.ogg

# 3. Transcribe, with no file in the body
curl -s -X POST https://sovrgpt.com/api/v1/audio/transcriptions \
  -H "Authorization: Bearer $SOVR_KEY" \
  -H "content-type: application/json" \
  -d '{"upload_id":"0f1c…","language":"de","response_format":"verbose_json","timestamp_granularities":"segment"}'

{ "text": "Hallo, dies ist ein Test." }

{
  "text": "Die Bundeswehr braucht eine souveräne Plattform. Der letzte Satz ist genau der, den wir prüfen wollen.",
  "language": "de",
  "duration": 7,
  "segments": [
    { "text": "Die Bundeswehr braucht eine souveräne Plattform.", "start": 0.5, "end": 3.3, "speakerId": null },
    { "text": "Der letzte Satz ist genau der, den wir prüfen wollen.", "start": 3.6, "end": 6.9, "speakerId": null }
  ]
}

curl https://sovrgpt.com/api/v1/audio/transcriptions \
  -H "Authorization: Bearer $SOVR_KEY" \
  -F file=@dictation.webm \
  -F format_text=1 \
  -F response_format=verbose_json

{
  "text": "Sehr geehrte Frau Dr. Schmitt,\n\nvielen Dank …\n\n1. Die Übertragung …\n2. Die Antwortzeiten …\n\nMit freundlichen Grüßen\nHans Elstner",
  "text_raw": "Sehr geehrte Frau Dr. Schmitt, vielen Dank … Erstens die Übertragung …",
  "language": null,
  "duration": 101,
  "formatting": { "applied": true, "verdict": "ok", "coverage": 0.996 }
}

from openai import OpenAI

client = OpenAI(base_url="https://sovrgpt.com/api/v1", api_key=SOVR_KEY)

# Text-to-speech (Supertonic, fast)
client.audio.speech.create(
    model="supertonic-3", voice="F3", response_format="wav",
    input="Hallo Welt <sigh> das war ein langer Tag.",
).stream_to_file("hello.wav")

# Text-to-speech (CosyVoice, German + emotion)
# model="cosyvoice-3" picks the engine; emotion (a SovrGPT extension) via extra_body
client.audio.speech.create(
    model="cosyvoice-3", voice="de-thorsten", response_format="wav",
    input="Was für ein wunderbarer Tag!",
    extra_body={"emotion": "Sprich fröhlich und aufgeregt."},
).stream_to_file("happy.wav")

# Speech-to-text
with open("recording.webm", "rb") as f:
    tr = client.audio.transcriptions.create(
        model="voxtral-mini-transcribe", file=f, language="de",
    )
print(tr.text)