{"query":"text to speech","count":4,"total":4,"results":[{"id":"fishaudio.tts.s2-1-pro","provider":"fishaudio","provider_display":"Fish Audio","name":"Fish Audio: S2.1 Pro text to speech","summary":"Generate audio from text, optionally using a reusable private voice owned by the current team.","method":"POST","path":"/v1/tts","scope":"any_account","tier":"core","kind":"data","domain":"models","call_template":"treg call fishaudio.tts.s2-1-pro --method POST --data '{\"text\":\"This is a Fish Audio test.\",\"format\":\"mp3\"}'","cost":{"type":"per_success","value":15,"currency":"USD","per":1000000,"unit":"utf8_byte","source":"docs","source_url":"https://docs.fish.audio/developer-guide/models-pricing/pricing-and-rate-limits","checked":"2026-09-21","confidence":"documented","note":"Fish bills S2.1 Pro by UTF-8 input bytes.","display":{"unit":"UTF-8 bytes","grouped":true},"usd":0.000015,"display_usd":15.0,"display_unit":"1M UTF-8 bytes","display_suffix":"","display_prefix":""},"async":null,"platform_eligible":true,"platform_blocked":null,"miss":null,"status":null,"status_note":null,"superseded_by":null,"verified":"2026-09-22","added":"2026-09-22","docs_url":"https://docs.fish.audio/api-reference/endpoint/openapi-v1/text-to-speech","has_example":true,"input":{"headers":{"model":{"type":"string","required":true,"enum":["s2.1-pro"],"example":"s2.1-pro"}},"body":{"text":{"type":"string","required":true,"min":1,"example":"Welcome to treg."},"reference_id":{"type":"string_or_array","required":false,"note":"Omit for Fish's default voice. On treg's key each id must be owned by the current team or verified by Fish as public."},"temperature":{"type":"number","required":false,"min":0,"max":1,"default":0.7},"top_p":{"type":"number","required":false,"min":0,"max":1,"default":0.7},"prosody":{"type":"object","required":false,"example":{"speed":1,"volume":0,"normalize_loudness":true},"properties":{"speed":{"type":"number","required":false,"min":0.5,"max":2,"default":1},"volume":{"type":"number","required":false,"default":0,"note":"Volume adjustment in decibels; Fish documents no numeric bound."},"normalize_loudness":{"type":"boolean","required":false,"default":true}}},"chunk_length":{"type":"integer","required":false,"min":100,"max":300,"default":300},"format":{"type":"string","required":false,"enum":["mp3","wav","pcm","opus"],"default":"mp3","example":"mp3"},"sample_rate":{"type":"integer","required":false,"enum":[8000,16000,24000,32000,44100,48000],"note":"Supported output rates depend on the selected format."},"mp3_bitrate":{"type":"integer","required":false,"enum":[64,128,192],"default":128},"opus_bitrate":{"type":"integer","required":false,"enum":[-1000,24000,32000,48000,64000],"default":-1000},"normalize":{"type":"boolean","required":false,"default":true},"latency":{"type":"string","required":false,"enum":["low","normal","balanced"],"default":"normal"},"max_new_tokens":{"type":"integer","required":false,"default":1024},"repetition_penalty":{"type":"number","required":false,"default":1.2},"min_chunk_length":{"type":"integer","required":false,"min":0,"max":100,"default":50},"condition_on_previous_chunks":{"type":"boolean","required":false,"default":true},"early_stop_threshold":{"type":"number","required":false,"min":0,"max":1,"default":1}},"bodyType":"json"},"test_request":{"headers":{"model":"s2.1-pro"},"body":{"text":"This is a Fish Audio test.","format":"mp3"}},"capability":"voice-gen.fishaudio.s2-1-pro.generate","capability_description":"Generate speech with Fish Audio S2.1 Pro","platform":"voice-gen","platform_label":"Voice generation","score":24.7599,"observed":{"samples":19282,"decided":18954,"ok_rate":0.9997,"p50_ms":1451,"p95_ms":14050,"last_ok_days":0,"hit_rate":null,"hit_samples":0}},{"id":"minimax.voice-gen.speech-2-8-turbo","provider":"minimax","provider_display":"MiniMax","name":"MiniMax: Speech 2.8 Turbo","summary":"Generate fast, cost-efficient speech from up to 10,000 characters of text.","method":"POST","path":"/v1/t2a_v2","scope":"any_account","tier":"core","kind":"data","domain":"models","call_template":"treg call minimax.voice-gen.speech-2-8-turbo --method POST --data '{\"model\":\"speech-2.8-turbo\",\"text\":\"Hello.\",\"stream\":false,\"output_format\":\"url\",\"voice_setting\":{\"voice_id\":\"English_expressive_narrator\",\"speed\":1,\"vol\":1,\"pitch\":0},\"audio_setting\":{\"sample_rate\":32000,\"bitrate\":128000,\"format\":\"mp3\",\"channel\":1}}'","cost":{"type":"per_success","value":0.6,"currency":"USD","per":10000,"unit":"character","display":{"unit":"characters","grouped":true},"source":"docs","source_url":"https://platform.minimax.io/docs/guides/pricing-paygo#audio","checked":"2026-09-18","confidence":"documented","note":"MiniMax bills synchronous Speech 2.8 Turbo by input characters at $60 per million ($0.60 per 10,000). Failed requests are not charged.","usd":0.00006,"display_usd":0.6,"display_unit":"10000 characters","display_suffix":"","display_prefix":""},"async":null,"platform_eligible":true,"platform_blocked":null,"miss":null,"status":null,"status_note":null,"superseded_by":null,"verified":null,"added":"2026-09-17","docs_url":"https://platform.minimax.io/docs/api-reference/speech-t2a-http","has_example":false,"input":{"body":{"model":{"type":"string","required":true,"enum":["speech-2.8-turbo"],"example":"speech-2.8-turbo"},"text":{"type":"string","required":true,"max":10000,"example":"A calm voice can make a complex idea feel simple.","note":"Fewer than 10,000 characters. Use <#x#> between speakable segments for a pause of x seconds."},"stream":{"type":"boolean","required":true,"enum":[false],"example":false,"note":"This catalog route is non-streaming so the relay returns one bounded JSON response."},"output_format":{"type":"string","required":true,"enum":["url"],"example":"url","note":"The returned audio URL is valid for 24 hours."},"voice_setting":{"type":"object","required":true,"example":{"voice_id":"English_expressive_narrator","speed":1,"vol":1,"pitch":0},"note":"voice_id is required. Optional controls include speed, vol, pitch, emotion, text_normalization and latex_read. speech-2.8 emotion is happy | sad | angry | fearful | disgusted | surprised | calm; whisper and fluent are 2.6-only (status 2013 on 2.8, even with a whispering-named voice_id — use a whispering-style voice_id instead, or speech-2.6 for emotion=whisper).","properties":{"voice_id":{"type":"string","required":true,"example":"English_expressive_narrator"},"speed":{"type":"number","required":false,"example":1},"vol":{"type":"number","required":false,"example":1},"pitch":{"type":"integer","required":false,"example":0},"emotion":{"type":"string","required":false,"enum":["happy","sad","angry","fearful","disgusted","surprised","calm"],"note":"speech-2.8 allows happy | sad | angry | fearful | disgusted | surprised | calm. whisper and fluent are 2.6-only and return status 2013 on 2.8 even with a whispering-named voice_id; use a whispering-style voice_id, or speech-2.6 for emotion=whisper."}}},"audio_setting":{"type":"object","required":false,"example":{"sample_rate":32000,"bitrate":128000,"format":"mp3","channel":1},"note":"Non-streaming output supports mp3, wav and flac. bitrate (mp3 only) is 32000 | 64000 | 128000 | 256000; 192000 is invalid (status 2013). sample_rate is 8000 | 16000 | 22050 | 24000 | 32000 | 44100.","properties":{"sample_rate":{"type":"integer","required":false,"example":32000,"enum":[8000,16000,22050,24000,32000,44100]},"bitrate":{"type":"integer","required":false,"example":128000,"enum":[32000,64000,128000,256000],"note":"mp3 only. 192000 is invalid (status 2013)."},"format":{"type":"string","required":false,"example":"mp3","note":"Non-streaming output supports mp3, wav and flac."},"channel":{"type":"integer","required":false,"example":1}}},"language_boost":{"type":"string","required":false,"example":"auto","enum":["Chinese","Chinese,Yue","English","Arabic","Russian","Spanish","French","Portuguese","German","Turkish","Dutch","Ukrainian","Vietnamese","Indonesian","Japanese","Italian","Korean","Thai","Polish","Romanian","Greek","Czech","Finnish","Hindi","Bulgarian","Danish","Hebrew","Malay","Persian","Slovak","Swedish","Croatian","Filipino","Hungarian","Norwegian","Slovenian","Catalan","Nynorsk","Tamil","Afrikaans","auto"],"note":"Exact enum strings only. English(UK) and en-GB are invalid (status 2013); use English. auto detects the language."},"pronunciation_dict":{"type":"object","required":false,"example":{"tone":["Treg/tree-g"]},"note":"Custom pronunciation pairs in source/target form."},"subtitle_enable":{"type":"boolean","required":false,"default":false},"subtitle_type":{"type":"string","required":false,"default":"sentence","enum":["sentence","word"],"example":"sentence"},"voice_modify":{"type":"object","required":false,"note":"Optional pitch, intensity, timbre and sound_effects controls."}},"bodyType":"json"},"test_request":{"body":{"model":"speech-2.8-turbo","text":"Hello.","stream":false,"output_format":"url","voice_setting":{"voice_id":"English_expressive_narrator","speed":1,"vol":1,"pitch":0},"audio_setting":{"sample_rate":32000,"bitrate":128000,"format":"mp3","channel":1}}},"capability":"voice-gen.speech-2-8-turbo.generate","capability_description":"MiniMax Speech 2.8 Turbo","platform":"voice-gen","platform_label":"Voice generation","score":24.7599,"observed":{"samples":9760,"decided":9760,"ok_rate":0.9999,"p50_ms":1915,"p95_ms":6387,"last_ok_days":0,"hit_rate":0.0,"hit_samples":30}},{"id":"minimax.voice-gen.speech-2-8-hd","provider":"minimax","provider_display":"MiniMax","name":"MiniMax: Speech 2.8 HD","summary":"Generate high-definition speech from up to 10,000 characters of text.","method":"POST","path":"/v1/t2a_v2","scope":"any_account","tier":"core","kind":"data","domain":"models","call_template":"treg call minimax.voice-gen.speech-2-8-hd --method POST --data '{\"model\":\"speech-2.8-hd\",\"text\":\"Hello.\",\"stream\":false,\"output_format\":\"url\",\"voice_setting\":{\"voice_id\":\"English_expressive_narrator\",\"speed\":1,\"vol\":1,\"pitch\":0},\"audio_setting\":{\"sample_rate\":32000,\"bitrate\":128000,\"format\":\"mp3\",\"channel\":1}}'","cost":{"type":"per_success","value":1.0,"currency":"USD","per":10000,"unit":"character","display":{"unit":"characters","grouped":true},"source":"docs","source_url":"https://platform.minimax.io/docs/guides/pricing-paygo#audio","checked":"2026-09-18","confidence":"documented","note":"MiniMax bills synchronous Speech 2.8 HD by input characters at $100 per million ($1 per 10,000). Failed requests are not charged.","usd":0.0001,"display_usd":1.0,"display_unit":"10000 characters","display_suffix":"","display_prefix":""},"async":null,"platform_eligible":true,"platform_blocked":null,"miss":null,"status":null,"status_note":null,"superseded_by":null,"verified":null,"added":"2026-09-17","docs_url":"https://platform.minimax.io/docs/api-reference/speech-t2a-http","has_example":false,"input":{"body":{"model":{"type":"string","required":true,"enum":["speech-2.8-hd"],"example":"speech-2.8-hd"},"text":{"type":"string","required":true,"max":10000,"example":"A calm voice can make a complex idea feel simple.","note":"Fewer than 10,000 characters. Use <#x#> between speakable segments for a pause of x seconds."},"stream":{"type":"boolean","required":true,"enum":[false],"example":false,"note":"This catalog route is non-streaming so the relay returns one bounded JSON response."},"output_format":{"type":"string","required":true,"enum":["url"],"example":"url","note":"The returned audio URL is valid for 24 hours."},"voice_setting":{"type":"object","required":true,"example":{"voice_id":"English_expressive_narrator","speed":1,"vol":1,"pitch":0},"note":"voice_id is required. Optional controls include speed, vol, pitch, emotion, text_normalization and latex_read. speech-2.8 emotion is happy | sad | angry | fearful | disgusted | surprised | calm; whisper and fluent are 2.6-only (status 2013 on 2.8, even with a whispering-named voice_id — use a whispering-style voice_id instead, or speech-2.6 for emotion=whisper).","properties":{"voice_id":{"type":"string","required":true,"example":"English_expressive_narrator"},"speed":{"type":"number","required":false,"example":1},"vol":{"type":"number","required":false,"example":1},"pitch":{"type":"integer","required":false,"example":0},"emotion":{"type":"string","required":false,"enum":["happy","sad","angry","fearful","disgusted","surprised","calm"],"note":"speech-2.8 allows happy | sad | angry | fearful | disgusted | surprised | calm. whisper and fluent are 2.6-only and return status 2013 on 2.8 even with a whispering-named voice_id; use a whispering-style voice_id, or speech-2.6 for emotion=whisper."}}},"audio_setting":{"type":"object","required":false,"example":{"sample_rate":32000,"bitrate":128000,"format":"mp3","channel":1},"note":"Non-streaming output supports mp3, wav and flac. bitrate (mp3 only) is 32000 | 64000 | 128000 | 256000; 192000 is invalid (status 2013). sample_rate is 8000 | 16000 | 22050 | 24000 | 32000 | 44100.","properties":{"sample_rate":{"type":"integer","required":false,"example":32000,"enum":[8000,16000,22050,24000,32000,44100]},"bitrate":{"type":"integer","required":false,"example":128000,"enum":[32000,64000,128000,256000],"note":"mp3 only. 192000 is invalid (status 2013)."},"format":{"type":"string","required":false,"example":"mp3","note":"Non-streaming output supports mp3, wav and flac."},"channel":{"type":"integer","required":false,"example":1}}},"language_boost":{"type":"string","required":false,"example":"auto","enum":["Chinese","Chinese,Yue","English","Arabic","Russian","Spanish","French","Portuguese","German","Turkish","Dutch","Ukrainian","Vietnamese","Indonesian","Japanese","Italian","Korean","Thai","Polish","Romanian","Greek","Czech","Finnish","Hindi","Bulgarian","Danish","Hebrew","Malay","Persian","Slovak","Swedish","Croatian","Filipino","Hungarian","Norwegian","Slovenian","Catalan","Nynorsk","Tamil","Afrikaans","auto"],"note":"Exact enum strings only. English(UK) and en-GB are invalid (status 2013); use English. auto detects the language."},"pronunciation_dict":{"type":"object","required":false,"example":{"tone":["Treg/tree-g"]},"note":"Custom pronunciation pairs in source/target form."},"subtitle_enable":{"type":"boolean","required":false,"default":false},"subtitle_type":{"type":"string","required":false,"default":"sentence","enum":["sentence","word"],"example":"sentence"},"voice_modify":{"type":"object","required":false,"note":"Optional pitch, intensity, timbre and sound_effects controls."}},"bodyType":"json"},"test_request":{"body":{"model":"speech-2.8-hd","text":"Hello.","stream":false,"output_format":"url","voice_setting":{"voice_id":"English_expressive_narrator","speed":1,"vol":1,"pitch":0},"audio_setting":{"sample_rate":32000,"bitrate":128000,"format":"mp3","channel":1}}},"capability":"voice-gen.speech-2-8-hd.generate","capability_description":"MiniMax Speech 2.8 HD","platform":"voice-gen","platform_label":"Voice generation","score":24.7599,"observed":{"samples":30351,"decided":30351,"ok_rate":0.9995,"p50_ms":1953,"p95_ms":5273,"last_ok_days":0,"hit_rate":0.0,"hit_samples":1083}},{"id":"scrapecreators.x.v2-instagram-media-transcript","provider":"scrapecreators","provider_display":"ScrapeCreators","name":"Instagram video or reel transcript by URL","summary":"Generates an AI-powered speech-to-text transcription for an Instagram video post or reel.","method":"GET","path":"/v2/instagram/media/transcript","scope":"","tier":"extended","kind":"data","domain":"media","call_template":"treg call scrapecreators.x.v2-instagram-media-transcript --query 'url=<string>' --query cache_max_age=7d","cost":{"type":"per_call","value":1,"currency":"credit","per":1,"unit":"call","reported_charge":{"path":"credits_charged","unit":"credit"},"source":"rate_card_api","source_url":"https://docs.scrapecreators.com/openapi.json","checked":"2026-07-28","confidence":"verified","usd":0.00188},"async":null,"platform_eligible":true,"platform_blocked":null,"miss":null,"status":null,"status_note":null,"superseded_by":null,"verified":null,"added":"2026-07-28","docs_url":"https://docs.scrapecreators.com/instagram/media/transcript","has_example":false,"input":{"queryParams":{"url":{"type":"string","required":true,"note":"Instagram post or reel URL"},"cache_max_age":{"type":"string","required":false,"note":"If we have a response in the cache that is this many days old or newer, return the cached response (0 credits, with \"cached\": true and a \"cached_at\" timestamp). Otherwise, scrape a live result (1 credit). [See the Cac...","example":"7d"}}},"test_request":{"queryParams":{"cache_max_age":"7d"}},"capability":"","capability_description":"","platform":"instagram","platform_label":"Instagram","score":18.4703,"observed":{"samples":66562,"decided":59467,"ok_rate":0.998,"p50_ms":5592,"p95_ms":9704,"last_ok_days":0,"hit_rate":null,"hit_samples":0}}],"hints":["treg catalog get fishaudio.tts.s2-1-pro   # params, cost and an example response","treg call fishaudio.tts.s2-1-pro --method POST --data '{\"text\":\"This is a Fish Audio test.\",\"format\":\"mp3\"}'   # run it — key injected server-side"]}