Skip to content

Self-improving AI Employees for everyone

12.5 KB
Raw Blame
{
  "_comment": "Per-provider speech capabilities. Sibling of llm_defaults.json and read the same way: services/speech/config.py loads this once at import and every capability lookup goes through it, so shared code never branches on a provider name. Values here were verified against live official docs; see docs-internal/speech_provider_rfc.md section 7 for the sources and for the handful of items the docs do not state. Per-model overrides use the same {'model-id': value, '_default': value} shape as llm_defaults.json's max_output_tokens.",
  "version": "1.0",
  "_common_languages_comment": "Fallback for the Language dropdown when a provider does not declare a closed list of its own. OpenAI/Whisper, Deepgram and Groq accept far more codes than these; this is a convenience shortlist, and 'Auto-detect' (empty value) is always offered first. A provider WITH a closed set (Sarvam) declares `languages` in its own block and that wins.",
  "common_languages": [
    "en", "es", "fr", "de", "it", "pt", "nl", "pl", "ru", "uk", "tr",
    "ar", "he", "fa", "hi", "bn", "ta", "te", "ur", "id", "vi", "th",
    "zh", "ja", "ko"
  ],
  "providers": {
    "openai": {
      "base_url": "https://api.openai.com/v1",
      "credential_id": "openai",
      "_gateway_comment": "Served by the OpenCompany Gateway when the install has no key of its own (nodes/speech/_base.py provider_key). The gateway's URL and LiteLLM model prefix come from this provider's gateway block in llm_defaults.json. It has no translation route, so translate falls back to in-language transcription there. gpt-4o-mini-tts is billed through a price override in gateway/litellm/config.yaml (the speech route returns no audio usage); tts-1 and tts-1-hd are billed per character, transcription per second.",
      "gateway": true,
      "tts": {
        "endpoint": "/audio/speech",
        "default_model": "gpt-4o-mini-tts",
        "models": ["gpt-4o-mini-tts", "tts-1", "tts-1-hd"],
        "_voices_comment": "13 voices exist, but tts-1 and tts-1-hd support only the first 9. Per-model override rather than a flat list so the node can validate before the provider 400s.",
        "voices": {
          "tts-1": ["alloy", "ash", "coral", "echo", "sage", "shimmer", "fable", "onyx", "nova"],
          "tts-1-hd": ["alloy", "ash", "coral", "echo", "sage", "shimmer", "fable", "onyx", "nova"],
          "_default": ["alloy", "ash", "ballad", "coral", "echo", "sage", "shimmer", "verse", "marin", "cedar", "fable", "onyx", "nova"]
        },
        "default_voice": "alloy",
        "output_formats": ["mp3", "opus", "aac", "flac", "wav", "pcm"],
        "default_output_format": "mp3",
        "speed_range": [0.25, 4.0],
        "max_input_chars": 4096,
        "billed_unit": "characters",
        "_instructions_comment": "Steerability via the `instructions` body field is gpt-4o-mini-tts only; it is silently ignored on tts-1 / tts-1-hd.",
        "supports_instructions": {
          "tts-1": false,
          "tts-1-hd": false,
          "_default": true
        }
      },
      "stt": {
        "endpoint": "/audio/transcriptions",
        "translate_endpoint": "/audio/translations",
        "default_model": "whisper-1",
        "models": ["whisper-1", "gpt-4o-transcribe", "gpt-4o-mini-transcribe", "gpt-4o-transcribe-diarize"],
        "_response_formats_comment": "Model-gated, and getting this wrong is a 400 rather than a degraded result. Because timestamp_granularities requires verbose_json, word timestamps are effectively whisper-1 only.",
        "response_formats": {
          "whisper-1": ["json", "text", "srt", "verbose_json", "vtt"],
          "gpt-4o-transcribe-diarize": ["json", "text", "diarized_json"],
          "_default": ["json", "text"]
        },
        "default_response_format": "json",
        "supports_timestamps": {
          "whisper-1": true,
          "_default": false
        },
        "supports_diarization": {
          "gpt-4o-transcribe-diarize": true,
          "_default": false
        },
        "supports_prompt": {
          "gpt-4o-transcribe-diarize": false,
          "_default": true
        },
        "max_upload_bytes": 26214400,
        "input_formats": ["flac", "mp3", "mp4", "mpeg", "mpga", "m4a", "ogg", "wav", "webm"],
        "billed_unit": "seconds"
      }
    },
    "groq": {
      "_comment": "Serves OpenAI's exact transcription wire format at its own base URL, so it rides the same provider class. Transcription-only: no TTS product.",
      "base_url": "https://api.groq.com/openai/v1",
      "credential_id": "groq",
      "_gateway_comment": "Not served by the OpenCompany Gateway: LiteLLM 1.103.4 bills Groq transcription at $0 (gateway/tests/test_gateway_contract.py test_groq_transcription_is_billed).",
      "stt": {
        "endpoint": "/audio/transcriptions",
        "translate_endpoint": "/audio/translations",
        "default_model": "whisper-large-v3-turbo",
        "models": ["whisper-large-v3-turbo", "whisper-large-v3"],
        "_translate_comment": "The turbo model omits translation entirely; only whisper-large-v3 can translate.",
        "supports_translate": {
          "whisper-large-v3-turbo": false,
          "_default": true
        },
        "response_formats": {
          "_default": ["json", "text", "verbose_json"]
        },
        "default_response_format": "json",
        "supports_timestamps": {
          "_default": true
        },
        "supports_diarization": {
          "_default": false
        },
        "max_prompt_tokens": 224,
        "max_upload_bytes": 26214400,
        "billed_unit": "seconds",
        "_min_billed_comment": "Groq bills a 10-second floor regardless of clip length; the provider reports max(duration, 10).",
        "min_billed_seconds": 10
      }
    },
    "elevenlabs": {
      "base_url": "https://api.elevenlabs.io",
      "credential_id": "elevenlabs",
      "tts": {
        "_endpoint_comment": "voice_id is a PATH segment, and output_format is a QUERY parameter rather than a body field. Sending output_format in the JSON body yields the default silently instead of an error.",
        "endpoint": "/v1/text-to-speech/{voice_id}",
        "voices_endpoint": "/v2/voices",
        "default_model": "eleven_multilingual_v2",
        "models": ["eleven_multilingual_v2", "eleven_v3", "eleven_flash_v2_5", "eleven_flash_v2", "eleven_ttv_v3"],
        "default_voice": "",
        "output_formats": [
          "mp3_22050_32", "mp3_24000_48", "mp3_44100_32", "mp3_44100_64",
          "mp3_44100_96", "mp3_44100_128", "mp3_44100_192",
          "opus_48000_32", "opus_48000_64", "opus_48000_96", "opus_48000_128", "opus_48000_192",
          "pcm_8000", "pcm_16000", "pcm_22050", "pcm_24000", "pcm_32000", "pcm_44100", "pcm_48000",
          "wav_8000", "wav_16000", "wav_22050", "wav_24000", "wav_32000", "wav_44100", "wav_48000",
          "alaw_8000", "ulaw_8000"
        ],
        "default_output_format": "mp3_44100_128",
        "_tier_gated_comment": "mp3 at 192 kbps needs Creator+; PCM and WAV at 44.1 kHz need Pro+. A tier miss surfaces as a permission error, which is why the panel does not pre-filter.",
        "_speed_comment": "The OpenAPI schema allows 0.5-2.0 while the best-practices guide recommends 0.7-1.2. Both are official and were never reconciled, so the API bound is enforced and the narrower range is guidance only.",
        "speed_range": [0.5, 2.0],
        "voice_settings_defaults": {
          "stability": 0.5,
          "similarity_boost": 0.75,
          "style": 0.0,
          "use_speaker_boost": true
        },
        "billed_unit": "characters"
      }
    },
    "deepgram": {
      "_comment": "Options are QUERY parameters, audio is sent as a RAW body with an audio/* Content-Type (not multipart), and auth is 'Authorization: Token <key>' rather than Bearer. All three differ from every other provider here.",
      "base_url": "https://api.deepgram.com/v1",
      "credential_id": "deepgram",
      "stt": {
        "endpoint": "/listen",
        "_default_model_comment": "Deepgram's own documented default is base-general, which is not what anyone wants in 2026, so an explicit default is set here rather than inherited.",
        "default_model": "nova-3",
        "models": [
          "nova-3", "nova-3-general", "nova-3-medical",
          "nova-2", "nova-2-meeting", "nova-2-phonecall", "nova-2-voicemail",
          "nova-2-finance", "nova-2-conversationalai", "nova-2-video", "nova-2-medical",
          "nova", "nova-general", "nova-phonecall",
          "whisper-large", "whisper-medium", "whisper-small", "whisper-base", "whisper-tiny"
        ],
        "supports_timestamps": {
          "_default": true
        },
        "supports_diarization": {
          "_default": true
        },
        "_smart_format_comment": "smart_format supersedes punctuate and additionally applies paragraphing plus number/date/currency formatting.",
        "default_smart_format": true,
        "_max_upload_comment": "VERIFIED from the Limits section of the pre-recorded-audio docs: 2 GB maximum file size. That is far above services.media's own 25 MiB read cap, which is therefore the binding limit in practice — the value is recorded for accuracy, not because it will ever be hit here. (An earlier revision claimed no cap was published; that was wrong.)",
        "max_upload_bytes": 2147483648,
        "_max_duration_comment": "ALSO verified, and this one bites: a synchronous request over 10 minutes of audio (Nova/Base/Enhanced) or 20 minutes (Whisper) returns 504 Gateway Timeout rather than a transcript. Long recordings need Deepgram's callback flow, which this node does not implement.",
        "max_duration_seconds": 600,
        "billed_unit": "minutes"
      }
    },
    "sarvam": {
      "_comment": "Indic-first. TTS returns base64 inside a JSON array rather than raw bytes, and long input comes back as several standalone clips that must not be byte-concatenated.",
      "base_url": "https://api.sarvam.ai",
      "credential_id": "sarvam",
      "tts": {
        "endpoint": "/text-to-speech",
        "default_model": "bulbul:v3",
        "models": ["bulbul:v3", "bulbul:v2"],
        "voices": {
          "bulbul:v2": ["anushka", "abhilash", "manisha", "vidya", "arya", "karun", "hitesh"],
          "_default": [
            "shubh", "aditya", "ritu", "priya", "neha", "rahul", "pooja", "rohan",
            "simran", "kavya", "amit", "dev", "ishita", "shreya", "ratan", "varun",
            "manan", "sumit", "roopa", "kabir", "aayan", "ashutosh", "advait", "anand",
            "tanya", "tarun", "sunny", "mani", "gokul", "vijay", "shruti", "suhani",
            "mohit", "kavitha", "rehan", "soham", "rupali"
          ]
        },
        "default_voice": "shubh",
        "languages": ["bn-IN", "en-IN", "gu-IN", "hi-IN", "kn-IN", "ml-IN", "mr-IN", "od-IN", "pa-IN", "ta-IN", "te-IN"],
        "default_language": "hi-IN",
        "output_formats": ["wav", "mp3", "linear16", "mulaw", "alaw", "opus", "flac", "aac"],
        "default_output_format": "wav",
        "max_input_chars": {
          "bulbul:v2": 1500,
          "_default": 2500
        },
        "speed_range": {
          "bulbul:v2": [0.3, 3.0],
          "_default": [0.5, 2.0]
        },
        "_sample_rate_comment": "Sarvam's own docs disagree with themselves here: the OpenAPI schema says 22050 while the field description says 24000. 24000 matches what the previous node shipped and what the description states.",
        "sample_rates": [8000, 16000, 22050, 24000, 32000, 44100, 48000],
        "default_sample_rate": 24000,
        "billed_unit": "characters"
      },
      "stt": {
        "endpoint": "/speech-to-text",
        "translate_endpoint": "/speech-to-text-translate",
        "default_model": "saaras:v3",
        "models": ["saaras:v3", "saarika:v2.5"],
        "_modes_comment": "Modes beyond transcribe/translate require saaras:v3.",
        "modes": ["transcribe", "translate", "verbatim", "translit", "codemix"],
        "_timestamps_comment": "Timestamps and diarization exist only on the batch job API, never on this synchronous endpoint. The response fields are always null here.",
        "supports_timestamps": {
          "_default": false
        },
        "supports_diarization": {
          "_default": false
        },
        "default_language": "unknown",
        "max_upload_bytes": 25165824,
        "billed_unit": "seconds"
      }
    }
  },
  "dictation": {
    "_comment": "Dictation in the chat's message box (nodes/speech/_handlers.py): the first of these speech-to-text providers with a stored key transcribes a recording (webm/opus from the browser). The microphone shows only when one has a key.",
    "providers": ["openai", "groq", "deepgram"]
  }
}