docs/openapi.json

{"openapi":"3.1.0","info":{"title":"FastAPI","version":"0.1.0"},"paths":{"/v1/audio/translations":{"post":{"tags":["automatic-speech-recognition"],"summary":"Translate File","operationId":"translate_file_v1_audio_translations_post","requestBody":{"content":{"application/x-www-form-urlencoded":{"schema":{"$ref":"#/components/schemas/Body_translate_file_v1_audio_translations_post"}}},"required":true},"responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"anyOf":[{"type":"string"},{"$ref":"#/components/schemas/CreateTranscriptionResponseJson"},{"$ref":"#/components/schemas/CreateTranscriptionResponseVerboseJson"}],"title":"Response Translate File V1 Audio Translations Post"}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}}}},"/v1/audio/transcriptions":{"post":{"tags":["automatic-speech-recognition"],"summary":"Transcribe File","operationId":"transcribe_file_v1_audio_transcriptions_post","requestBody":{"content":{"application/x-www-form-urlencoded":{"schema":{"$ref":"#/components/schemas/Body_transcribe_file_v1_audio_transcriptions_post"}}},"required":true},"responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"anyOf":[{"type":"string"},{"$ref":"#/components/schemas/CreateTranscriptionResponseJson"},{"$ref":"#/components/schemas/CreateTranscriptionResponseVerboseJson"}],"title":"Response Transcribe File V1 Audio Transcriptions Post"}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}}}},"/v1/models":{"get":{"tags":["models"],"summary":"Get Models","operationId":"get_models_v1_models_get","responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ListModelsResponse"}}}}}}},"/v1/models/{model_name}":{"get":{"tags":["models"],"summary":"Get Model","operationId":"get_model_v1_models__model_name__get","parameters":[{"name":"model_name","in":"path","required":true,"schema":{"type":"string","title":"Model Name"},"example":"Systran/faster-distil-whisper-large-v3"}],"responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Model"}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}}}},"/health":{"get":{"tags":["diagnostic"],"summary":"Health","operationId":"health_health_get","responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{}}}}}}},"/api/pull/{model_name}":{"post":{"tags":["experimental"],"summary":"Download a model from Hugging Face.","operationId":"pull_model_api_pull__model_name__post","parameters":[{"name":"model_name","in":"path","required":true,"schema":{"type":"string","title":"Model Name"}}],"responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}}}},"/api/ps":{"get":{"tags":["experimental"],"summary":"Get a list of loaded models.","operationId":"get_running_models_api_ps_get","responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"additionalProperties":{"items":{"type":"string"},"type":"array"},"type":"object","title":"Response Get Running Models Api Ps Get"}}}}}}},"/api/ps/{model_name}":{"post":{"tags":["experimental"],"summary":"Load a model into memory.","operationId":"load_model_route_api_ps__model_name__post","parameters":[{"name":"model_name","in":"path","required":true,"schema":{"type":"string","title":"Model Name"}}],"responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}}},"delete":{"tags":["experimental"],"summary":"Unload a model from memory.","operationId":"stop_running_model_api_ps__model_name__delete","parameters":[{"name":"model_name","in":"path","required":true,"schema":{"type":"string","title":"Model Name"}}],"responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}}}},"/v1/audio/speech":{"post":{"tags":["speech-to-text"],"summary":"Synthesize","operationId":"synthesize_v1_audio_speech_post","requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/CreateSpeechRequestBody"}}},"required":true},"responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}}}},"/v1/audio/speech/voices":{"get":{"tags":["speech-to-text"],"summary":"List Voices","operationId":"list_voices_v1_audio_speech_voices_get","responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"items":{"$ref":"#/components/schemas/PiperModel"},"type":"array","title":"Response List Voices V1 Audio Speech Voices Get"}}}}}}}},"components":{"schemas":{"Body_transcribe_file_v1_audio_transcriptions_post":{"properties":{"model":{"anyOf":[{"type":"string","description":"The ID of the model. You can get a list of available models by calling `/v1/models`.","examples":["Systran/faster-distil-whisper-large-v3","bofenghuang/whisper-large-v2-cv11-french-ct2"]},{"type":"null"}],"title":"Model"},"language":{"anyOf":[{"$ref":"#/components/schemas/Language"},{"type":"null"}]},"prompt":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Prompt"},"response_format":{"anyOf":[{"$ref":"#/components/schemas/faster_whisper_server__config__ResponseFormat"},{"type":"null"}]},"temperature":{"type":"number","title":"Temperature","default":0.0},"timestamp_granularities":{"items":{"type":"string","enum":["segment","word"]},"type":"array","title":"Timestamp Granularities","default":["segment"]},"stream":{"type":"boolean","title":"Stream","default":false},"hotwords":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Hotwords"},"vad_filter":{"type":"boolean","title":"Vad Filter","default":false},"file":{"type":"string","format":"binary","title":"File"}},"type":"object","required":["file"],"title":"Body_transcribe_file_v1_audio_transcriptions_post"},"Body_translate_file_v1_audio_translations_post":{"properties":{"model":{"anyOf":[{"type":"string","description":"The ID of the model. You can get a list of available models by calling `/v1/models`.","examples":["Systran/faster-distil-whisper-large-v3","bofenghuang/whisper-large-v2-cv11-french-ct2"]},{"type":"null"}],"title":"Model"},"prompt":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Prompt"},"response_format":{"anyOf":[{"$ref":"#/components/schemas/faster_whisper_server__config__ResponseFormat"},{"type":"null"}]},"temperature":{"type":"number","title":"Temperature","default":0.0},"stream":{"type":"boolean","title":"Stream","default":false},"vad_filter":{"type":"boolean","title":"Vad Filter","default":false},"file":{"type":"string","format":"binary","title":"File"}},"type":"object","required":["file"],"title":"Body_translate_file_v1_audio_translations_post"},"CreateSpeechRequestBody":{"properties":{"model":{"type":"string","enum":["piper"],"const":"piper","title":"Model","description":"The ID of the model. The only supported model is 'piper'.","default":"piper","examples":["piper"]},"input":{"type":"string","title":"Input","description":"The text to generate audio for. ","examples":["A rainbow is an optical phenomenon caused by refraction, internal reflection and dispersion of light in water droplets resulting in a continuous spectrum of light appearing in the sky. The rainbow takes the form of a multicoloured circular arc. Rainbows caused by sunlight always appear in the section of sky directly opposite the Sun. Rainbows can be caused by many forms of airborne water. These include not only rain, but also mist, spray, and airborne dew."]},"voice":{"type":"string","title":"Voice","default":"en_US-amy-medium"},"response_format":{"$ref":"#/components/schemas/faster_whisper_server__routers__speech__ResponseFormat","description":"The format to audio in. Supported formats are mp3, flac, wav, pcm. opus, aac are not supported","default":"mp3","examples":["mp3","flac","wav","pcm"]},"speed":{"type":"number","maximum":4.0,"minimum":0.25,"title":"Speed","default":1.0},"sample_rate":{"anyOf":[{"type":"integer","maximum":48000.0,"minimum":8000.0},{"type":"null"}],"title":"Sample Rate"}},"type":"object","required":["input"],"title":"CreateSpeechRequestBody"},"CreateTranscriptionResponseJson":{"properties":{"text":{"type":"string","title":"Text"}},"type":"object","required":["text"],"title":"CreateTranscriptionResponseJson"},"CreateTranscriptionResponseVerboseJson":{"properties":{"task":{"type":"string","title":"Task","default":"transcribe"},"language":{"type":"string","title":"Language"},"duration":{"type":"number","title":"Duration"},"text":{"type":"string","title":"Text"},"words":{"anyOf":[{"items":{"$ref":"#/components/schemas/TranscriptionWord"},"type":"array"},{"type":"null"}],"title":"Words"},"segments":{"items":{"$ref":"#/components/schemas/TranscriptionSegment"},"type":"array","title":"Segments"}},"type":"object","required":["language","duration","text","words","segments"],"title":"CreateTranscriptionResponseVerboseJson"},"HTTPValidationError":{"properties":{"detail":{"items":{"$ref":"#/components/schemas/ValidationError"},"type":"array","title":"Detail"}},"type":"object","title":"HTTPValidationError"},"Language":{"type":"string","enum":["af","am","ar","as","az","ba","be","bg","bn","bo","br","bs","ca","cs","cy","da","de","el","en","es","et","eu","fa","fi","fo","fr","gl","gu","ha","haw","he","hi","hr","ht","hu","hy","id","is","it","ja","jw","ka","kk","km","kn","ko","la","lb","ln","lo","lt","lv","mg","mi","mk","ml","mn","mr","ms","mt","my","ne","nl","nn","no","oc","pa","pl","ps","pt","ro","ru","sa","sd","si","sk","sl","sn","so","sq","sr","su","sv","sw","ta","te","tg","th","tk","tl","tr","tt","uk","ur","uz","vi","yi","yo","yue","zh"],"title":"Language"},"ListModelsResponse":{"properties":{"data":{"items":{"$ref":"#/components/schemas/Model"},"type":"array","title":"Data"},"object":{"type":"string","enum":["list"],"const":"list","title":"Object","default":"list"}},"type":"object","required":["data"],"title":"ListModelsResponse"},"Model":{"properties":{"id":{"type":"string","title":"Id"},"created":{"type":"integer","title":"Created"},"object":{"type":"string","enum":["model"],"const":"model","title":"Object"},"owned_by":{"type":"string","title":"Owned By"},"language":{"items":{"type":"string"},"type":"array","title":"Language"}},"type":"object","required":["id","created","object","owned_by"],"title":"Model","examples":[{"created":1700732060,"id":"Systran/faster-whisper-large-v3","object":"model","owned_by":"Systran"},{"created":1711378296,"id":"Systran/faster-distil-whisper-large-v3","object":"model","owned_by":"Systran"},{"created":1687968011,"id":"bofenghuang/whisper-large-v2-cv11-french-ct2","object":"model","owned_by":"bofenghuang"}]},"PiperModel":{"properties":{"object":{"type":"string","enum":["model"],"const":"model","title":"Object","default":"model"},"created":{"type":"integer","title":"Created"},"owned_by":{"type":"string","enum":["rhasspy"],"const":"rhasspy","title":"Owned By","default":"rhasspy"},"model_path":{"type":"string","format":"path","title":"Model Path","examples":["/home/nixos/.cache/huggingface/hub/models--rhasspy--piper-voices/snapshots/3d796cc2f2c884b3517c527507e084f7bb245aea/en/en_US/amy/medium/en_US-amy-medium.onnx"]},"id":{"type":"string","title":"Id","readOnly":true,"examples":["rhasspy/piper-voices/en_US-amy-medium"]},"voice":{"type":"string","title":"Voice","readOnly":true,"examples":["rhasspy/piper-voices/en_US-amy-medium"]},"config_path":{"type":"string","format":"path","title":"Config Path","readOnly":true},"quality":{"type":"string","enum":["x_low","low","medium","high"],"title":"Quality","readOnly":true},"sample_rate":{"type":"integer","title":"Sample Rate","readOnly":true}},"type":"object","required":["created","model_path","id","voice","config_path","quality","sample_rate"],"title":"PiperModel","description":"Similar structure to the GET /v1/models response but with extra fields."},"TranscriptionSegment":{"properties":{"id":{"type":"integer","title":"Id"},"seek":{"type":"integer","title":"Seek"},"start":{"type":"number","title":"Start"},"end":{"type":"number","title":"End"},"text":{"type":"string","title":"Text"},"tokens":{"items":{"type":"integer"},"type":"array","title":"Tokens"},"temperature":{"type":"number","title":"Temperature"},"avg_logprob":{"type":"number","title":"Avg Logprob"},"compression_ratio":{"type":"number","title":"Compression Ratio"},"no_speech_prob":{"type":"number","title":"No Speech Prob"},"words":{"anyOf":[{"items":{"$ref":"#/components/schemas/TranscriptionWord"},"type":"array"},{"type":"null"}],"title":"Words"}},"type":"object","required":["id","seek","start","end","text","tokens","temperature","avg_logprob","compression_ratio","no_speech_prob","words"],"title":"TranscriptionSegment"},"TranscriptionWord":{"properties":{"start":{"type":"number","title":"Start"},"end":{"type":"number","title":"End"},"word":{"type":"string","title":"Word"},"probability":{"type":"number","title":"Probability"}},"type":"object","required":["start","end","word","probability"],"title":"TranscriptionWord"},"ValidationError":{"properties":{"loc":{"items":{"anyOf":[{"type":"string"},{"type":"integer"}]},"type":"array","title":"Location"},"msg":{"type":"string","title":"Message"},"type":{"type":"string","title":"Error Type"}},"type":"object","required":["loc","msg","type"],"title":"ValidationError"},"faster_whisper_server__config__ResponseFormat":{"type":"string","enum":["text","json","verbose_json","srt","vtt"],"title":"ResponseFormat"},"faster_whisper_server__routers__speech__ResponseFormat":{"type":"string","enum":["mp3","flac","wav","pcm"]}}},"tags":[{"name":"automatic-speech-recognition"},{"name":"speech-to-text"},{"name":"models"},{"name":"diagnostic"},{"name":"experimental","description":"Not meant for public use yet. May change or be removed at any time."}]}