{ "aboutHtml": "

Speech 2.6 Turbo ialah edisi pertuturan MiniMax tepat yang dipilih oleh model: "minimax/speech-2.6-turbo". Gunakan POST /v1/audio/speech dengan badan application/json yang mengandungi model dan text untuk dituturkan. Inputnya ialah skrip bertulis dan hasilnya ialah audio sintesis. Untuk mesej aplikasi, bekalkan perkataan tepat yang perlu didengar oleh pendengar dan eja penuh sebarang singkatan yang kabur. Untuk pelajaran pendek, asingkan penerangan daripada contoh dalam skrip itu sendiri. Untuk aliran antara muka bernarasi, kaitkan setiap segmen lisan dengan tindakan pengguna yang khusus dan simpan skrip bersama audionya.

Medan text mestilah tidak kosong dan mengandungi kurang daripada 10,000 aksara Unicode. Hantar skrip lisan lengkap dengan stream:false, atau jangan sertakan stream. Bahagikan bahan yang lebih panjang kepada segmen skrip lengkap yang berasingan sebelum menyerahkan setiap segmen. Dokumen boleh digunakan dengan membaca kandungan sebenarnya dan meletakkan petikan yang berkaitan dalam text; URL dokumen bukan pengganti skrip.

Pilih suara melalui voice_setting.voice_id. Kategori suara yang didokumenkan merangkumi suara sistem serta suara yang telah diklon atau direka melalui teks; gunakan ID suara yang sah untuk kategori yang dipilih. Suara contoh ialah audiobook_male_1. Objek yang sama mengawal speed dari 0.5 hingga 2, vol melebihi 0 hingga 10, dan pitch integer dari -12 hingga 12. Nilai lalainya ialah 1, 1 dan 0. Kawalan ini melaraskan aspek penyampaian lisan yang berbeza, jadi pilih secara berasingan dan bukannya meletakkan namanya dalam skrip.

voice_setting.emotion menerima happy, sad, angry, fearful, disgusted, surprised, calm dan fluent. Dokumentasi turut menerangkan pemadanan emosi secara automatik daripada teks. Untuk skrip yang banyak nombor, voice_setting.text_normalization mengaktifkan penormalan teks bahasa Cina dan Inggeris serta mempunyai nilai lalai false. voice_setting.latex_read mengawal bacaan ungkapan LaTeX dan turut mempunyai nilai lalai false. pronunciation_dict.tone ialah tatasusunan rentetan peraturan sebutan. Contoh yang diterbitkan ialah ["草地/(cao3)(di1)"]; kekalkan perkataan, garis miring dan struktur sebutan dalam kurungan apabila membekalkan peraturan.

audio_setting.format menerima mp3, pcm, flac dan wav, dengan mp3 sebagai nilai lalai. sample_rate menerima 8000, 16000, 22050, 24000, 32000 dan 44100 Hz; nilai lalainya ialah 32000. channel ialah 1 untuk mono atau 2 untuk dua saluran, dengan nilai lalai 1. Nilai bitrate ialah 32000, 64000, 128000 dan 256000 bit sesaat, dengan nilai lalai 128000, dan terpakai pada mp3. Pilih pengekodan yang diperlukan oleh pemain atau alat penyuntingan yang akan menggunakan hasil.

language_boost ialah rentetan pilihan dan mempunyai nilai lalai null. Nilai yang dibenarkan ialah 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 dan auto. "Chinese,Yue" ialah satu nilai. Ia ialah kawalan yang berasingan daripada skrip dan ID suara. Skema turut menyediakan timber_weights untuk senarai pasangan voice_id dan weight integer, dengan setiap weight dari 1 hingga 100. Kekalkan ejaan parameter timber_weights semasa menyediakan permintaan. voice_modify.sound_effects ialah rentetan pilihan dengan nilai spacious_echo, auditorium_echo, lofi_telephone dan robotic.

Nilai lalai stream ialah false. Untuk balasan lengkap, output_format memilih url atau hex dan mempunyai nilai lalai hex. Dalam hasil JSON yang didokumenkan, data.audio membawa perwakilan yang dipilih: muat turun URL Ailoot bertandatangan yang lengkap, termasuk rentetan pertanyaannya, atau nyahkod audio perenambelasan yang lengkap menjadi bait. Simpan hasil asal bersama data.status, base_resp, trace_id dan extra_info, yang merangkumi format audio sebenar, kadar sampel, bilangan saluran, saiz dan usage_characters.

subtitle_enable ialah boolean yang mempunyai nilai lalai false dan terpakai pada output tanpa penstriman. aigc_watermark ialah boolean yang mempunyai nilai lalai false dan mengawal penanda irama yang boleh didengar pada hujung audio terjana. Simpan setiap hasil audio atau sari kata yang dikembalikan, dan semak sebutan, nombor serta fail yang telah siap sebelum meletakkannya dalam aplikasi. Jika penghantaran tidak pasti, simpan pengecam permintaan asal dan balasan untuk menyemak percubaan sedia ada. Ailoot turut menyimpan audio yang telah siap dalam pustaka media anda. Dengan output_format:"url", data.audio mengandungi pautan bertandatangan ke aset yang disimpan itu; ID aset muncul dalam laluan /v1/media/assets/{asset_id}/content. Pautan fail Ailoot bertandatangan sah selama 24 jam dari masa dikeluarkan. Gunakan kunci API yang sama untuk GET /v1/media/assets?family=audio dan ikuti setiap next_cursor untuk mencari rekod aset audio. Baca GET /v1/media/assets/{asset_id} bagi setiap rekod yang dipilih dan muat turun content_url tepatnya, termasuk rentetan pertanyaan. Jika permintaan fail mengembalikan 404 dengan kod link_expired, baca semula aset yang sama untuk mendapatkan content_url yang diperbaharui. Perbaharui hasil yang disimpan dan bukannya menjana audio semula untuk menggantikan pautan luput.

", "aboutText": "Speech 2.6 Turbo ialah edisi pertuturan MiniMax tepat yang dipilih oleh model: \"minimax/speech-2.6-turbo\". Gunakan POST /v1/audio/speech dengan badan application/json yang mengandungi model dan text untuk dituturkan. Inputnya ialah skrip bertulis dan hasilnya ialah audio sintesis. Untuk mesej aplikasi, bekalkan perkataan tepat yang perlu didengar oleh pendengar dan eja penuh sebarang singkatan yang kabur. Untuk pelajaran pendek, asingkan penerangan daripada contoh dalam skrip itu sendiri. Untuk aliran antara muka bernarasi, kaitkan setiap segmen lisan dengan tindakan pengguna yang khusus dan simpan skrip bersama audionya.\n\nMedan text mestilah tidak kosong dan mengandungi kurang daripada 10,000 aksara Unicode. Hantar skrip lisan lengkap dengan stream:false, atau jangan sertakan stream. Bahagikan bahan yang lebih panjang kepada segmen skrip lengkap yang berasingan sebelum menyerahkan setiap segmen. Dokumen boleh digunakan dengan membaca kandungan sebenarnya dan meletakkan petikan yang berkaitan dalam text; URL dokumen bukan pengganti skrip.\n\nPilih suara melalui voice_setting.voice_id. Kategori suara yang didokumenkan merangkumi suara sistem serta suara yang telah diklon atau direka melalui teks; gunakan ID suara yang sah untuk kategori yang dipilih. Suara contoh ialah audiobook_male_1. Objek yang sama mengawal speed dari 0.5 hingga 2, vol melebihi 0 hingga 10, dan pitch integer dari -12 hingga 12. Nilai lalainya ialah 1, 1 dan 0. Kawalan ini melaraskan aspek penyampaian lisan yang berbeza, jadi pilih secara berasingan dan bukannya meletakkan namanya dalam skrip.\n\nvoice_setting.emotion menerima happy, sad, angry, fearful, disgusted, surprised, calm dan fluent. Dokumentasi turut menerangkan pemadanan emosi secara automatik daripada teks. Untuk skrip yang banyak nombor, voice_setting.text_normalization mengaktifkan penormalan teks bahasa Cina dan Inggeris serta mempunyai nilai lalai false. voice_setting.latex_read mengawal bacaan ungkapan LaTeX dan turut mempunyai nilai lalai false. pronunciation_dict.tone ialah tatasusunan rentetan peraturan sebutan. Contoh yang diterbitkan ialah [\"草地/(cao3)(di1)\"]; kekalkan perkataan, garis miring dan struktur sebutan dalam kurungan apabila membekalkan peraturan.\n\naudio_setting.format menerima mp3, pcm, flac dan wav, dengan mp3 sebagai nilai lalai. sample_rate menerima 8000, 16000, 22050, 24000, 32000 dan 44100 Hz; nilai lalainya ialah 32000. channel ialah 1 untuk mono atau 2 untuk dua saluran, dengan nilai lalai 1. Nilai bitrate ialah 32000, 64000, 128000 dan 256000 bit sesaat, dengan nilai lalai 128000, dan terpakai pada mp3. Pilih pengekodan yang diperlukan oleh pemain atau alat penyuntingan yang akan menggunakan hasil.\n\nlanguage_boost ialah rentetan pilihan dan mempunyai nilai lalai null. Nilai yang dibenarkan ialah 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 dan auto. \"Chinese,Yue\" ialah satu nilai. Ia ialah kawalan yang berasingan daripada skrip dan ID suara. Skema turut menyediakan timber_weights untuk senarai pasangan voice_id dan weight integer, dengan setiap weight dari 1 hingga 100. Kekalkan ejaan parameter timber_weights semasa menyediakan permintaan. voice_modify.sound_effects ialah rentetan pilihan dengan nilai spacious_echo, auditorium_echo, lofi_telephone dan robotic.\n\nNilai lalai stream ialah false. Untuk balasan lengkap, output_format memilih url atau hex dan mempunyai nilai lalai hex. Dalam hasil JSON yang didokumenkan, data.audio membawa perwakilan yang dipilih: muat turun URL Ailoot bertandatangan yang lengkap, termasuk rentetan pertanyaannya, atau nyahkod audio perenambelasan yang lengkap menjadi bait. Simpan hasil asal bersama data.status, base_resp, trace_id dan extra_info, yang merangkumi format audio sebenar, kadar sampel, bilangan saluran, saiz dan usage_characters.\n\nsubtitle_enable ialah boolean yang mempunyai nilai lalai false dan terpakai pada output tanpa penstriman. aigc_watermark ialah boolean yang mempunyai nilai lalai false dan mengawal penanda irama yang boleh didengar pada hujung audio terjana. Simpan setiap hasil audio atau sari kata yang dikembalikan, dan semak sebutan, nombor serta fail yang telah siap sebelum meletakkannya dalam aplikasi. Jika penghantaran tidak pasti, simpan pengecam permintaan asal dan balasan untuk menyemak percubaan sedia ada. Ailoot turut menyimpan audio yang telah siap dalam pustaka media anda. Dengan output_format:\"url\", data.audio mengandungi pautan bertandatangan ke aset yang disimpan itu; ID aset muncul dalam laluan /v1/media/assets/{asset_id}/content. Pautan fail Ailoot bertandatangan sah selama 24 jam dari masa dikeluarkan. Gunakan kunci API yang sama untuk GET /v1/media/assets?family=audio dan ikuti setiap next_cursor untuk mencari rekod aset audio. Baca GET /v1/media/assets/{asset_id} bagi setiap rekod yang dipilih dan muat turun content_url tepatnya, termasuk rentetan pertanyaan. Jika permintaan fail mengembalikan 404 dengan kod link_expired, baca semula aset yang sama untuk mendapatkan content_url yang diperbaharui. Perbaharui hasil yang disimpan dan bukannya menjana audio semula untuk menggantikan pautan luput.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "3b5142e14de4405bf160d718eb26910ec834d0165e4c59461c78fd512b5accd0", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "ms", "methods": [ { "html": "
MM

MiniMax: Speech 2.6 Turbo

MiniMax /minimax/speech-2.6-turbo

Pengenalan

Speech 2.6 Turbo ialah model teks-ke-pertuturan MiniMax untuk mengubah skrip yang telah siap menjadi audio. Edisi minimax/speech-2.6-turbo menyediakan kawalan suara, penyampaian dan format audio, dengan balasan JSON lengkap serta pilihan output audio URL atau perenambelasan. Gunakannya untuk mencipta versi lisan mesej, pelajaran pendek atau skrip aplikasi yang dibekalkan.

Input yang diterima
Teks
Hasil
Audio
Tentang model

Huraian ini merangkumi keupayaan model. Input, output dan pilihan yang tersedia di Ailoot disenaraikan di bawah untuk kaedah yang dipilih.

Speech 2.6 Turbo ialah edisi pertuturan MiniMax tepat yang dipilih oleh model: "minimax/speech-2.6-turbo". Gunakan POST /v1/audio/speech dengan badan application/json yang mengandungi model dan text untuk dituturkan. Inputnya ialah skrip bertulis dan hasilnya ialah audio sintesis. Untuk mesej aplikasi, bekalkan perkataan tepat yang perlu didengar oleh pendengar dan eja penuh sebarang singkatan yang kabur. Untuk pelajaran pendek, asingkan penerangan daripada contoh dalam skrip itu sendiri. Untuk aliran antara muka bernarasi, kaitkan setiap segmen lisan dengan tindakan pengguna yang khusus dan simpan skrip bersama audionya.

Medan text mestilah tidak kosong dan mengandungi kurang daripada 10,000 aksara Unicode. Hantar skrip lisan lengkap dengan stream:false, atau jangan sertakan stream. Bahagikan bahan yang lebih panjang kepada segmen skrip lengkap yang berasingan sebelum menyerahkan setiap segmen. Dokumen boleh digunakan dengan membaca kandungan sebenarnya dan meletakkan petikan yang berkaitan dalam text; URL dokumen bukan pengganti skrip.

Pilih suara melalui voice_setting.voice_id. Kategori suara yang didokumenkan merangkumi suara sistem serta suara yang telah diklon atau direka melalui teks; gunakan ID suara yang sah untuk kategori yang dipilih. Suara contoh ialah audiobook_male_1. Objek yang sama mengawal speed dari 0.5 hingga 2, vol melebihi 0 hingga 10, dan pitch integer dari -12 hingga 12. Nilai lalainya ialah 1, 1 dan 0. Kawalan ini melaraskan aspek penyampaian lisan yang berbeza, jadi pilih secara berasingan dan bukannya meletakkan namanya dalam skrip.

voice_setting.emotion menerima happy, sad, angry, fearful, disgusted, surprised, calm dan fluent. Dokumentasi turut menerangkan pemadanan emosi secara automatik daripada teks. Untuk skrip yang banyak nombor, voice_setting.text_normalization mengaktifkan penormalan teks bahasa Cina dan Inggeris serta mempunyai nilai lalai false. voice_setting.latex_read mengawal bacaan ungkapan LaTeX dan turut mempunyai nilai lalai false. pronunciation_dict.tone ialah tatasusunan rentetan peraturan sebutan. Contoh yang diterbitkan ialah ["草地/(cao3)(di1)"]; kekalkan perkataan, garis miring dan struktur sebutan dalam kurungan apabila membekalkan peraturan.

audio_setting.format menerima mp3, pcm, flac dan wav, dengan mp3 sebagai nilai lalai. sample_rate menerima 8000, 16000, 22050, 24000, 32000 dan 44100 Hz; nilai lalainya ialah 32000. channel ialah 1 untuk mono atau 2 untuk dua saluran, dengan nilai lalai 1. Nilai bitrate ialah 32000, 64000, 128000 dan 256000 bit sesaat, dengan nilai lalai 128000, dan terpakai pada mp3. Pilih pengekodan yang diperlukan oleh pemain atau alat penyuntingan yang akan menggunakan hasil.

language_boost ialah rentetan pilihan dan mempunyai nilai lalai null. Nilai yang dibenarkan ialah 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 dan auto. "Chinese,Yue" ialah satu nilai. Ia ialah kawalan yang berasingan daripada skrip dan ID suara. Skema turut menyediakan timber_weights untuk senarai pasangan voice_id dan weight integer, dengan setiap weight dari 1 hingga 100. Kekalkan ejaan parameter timber_weights semasa menyediakan permintaan. voice_modify.sound_effects ialah rentetan pilihan dengan nilai spacious_echo, auditorium_echo, lofi_telephone dan robotic.

Nilai lalai stream ialah false. Untuk balasan lengkap, output_format memilih url atau hex dan mempunyai nilai lalai hex. Dalam hasil JSON yang didokumenkan, data.audio membawa perwakilan yang dipilih: muat turun URL Ailoot bertandatangan yang lengkap, termasuk rentetan pertanyaannya, atau nyahkod audio perenambelasan yang lengkap menjadi bait. Simpan hasil asal bersama data.status, base_resp, trace_id dan extra_info, yang merangkumi format audio sebenar, kadar sampel, bilangan saluran, saiz dan usage_characters.

subtitle_enable ialah boolean yang mempunyai nilai lalai false dan terpakai pada output tanpa penstriman. aigc_watermark ialah boolean yang mempunyai nilai lalai false dan mengawal penanda irama yang boleh didengar pada hujung audio terjana. Simpan setiap hasil audio atau sari kata yang dikembalikan, dan semak sebutan, nombor serta fail yang telah siap sebelum meletakkannya dalam aplikasi. Jika penghantaran tidak pasti, simpan pengecam permintaan asal dan balasan untuk menyemak percubaan sedia ada. Ailoot turut menyimpan audio yang telah siap dalam pustaka media anda. Dengan output_format:"url", data.audio mengandungi pautan bertandatangan ke aset yang disimpan itu; ID aset muncul dalam laluan /v1/media/assets/{asset_id}/content. Pautan fail Ailoot bertandatangan sah selama 24 jam dari masa dikeluarkan. Gunakan kunci API yang sama untuk GET /v1/media/assets?family=audio dan ikuti setiap next_cursor untuk mencari rekod aset audio. Baca GET /v1/media/assets/{asset_id} bagi setiap rekod yang dipilih dan muat turun content_url tepatnya, termasuk rentetan pertanyaan. Jika permintaan fail mengembalikan 404 dengan kod link_expired, baca semula aset yang sama untuk mendapatkan content_url yang diperbaharui. Perbaharui hasil yang disimpan dan bukannya menjana audio semula untuk menggantikan pautan luput.

Tersedia di Ailoot · input & kaedah

Ailoot Ultra · Speech POST /v1/audio/speech
Input
text
Output
audio
Format output
mp3,pcm,flac,wav
MedanJenisKeperluanNilai & hadLalai
MedanmodelJenisstringKeperluanDiperlukanNilai & had
minimax/speech-2.6-turbo
Lalai—
MedantextJenisstringKeperluanDiperlukanNilai & hadLalai—
MedanstreamJenisbooleanKeperluanPilihanNilai & had
false
Lalaifalse
Medanvoice_settingJenisobjectKeperluanPilihanNilai & hadLalai—
Medanvoice_setting.voice_idJenisstringKeperluanPilihanNilai & hadLalai—
Medanvoice_setting.speedJenisnumberKeperluanPilihanNilai & had
Minimum: 0.5
Maksimum: 2
Lalai1
Medanvoice_setting.volJenisnumberKeperluanPilihanNilai & had
Minimum: 0
Maksimum: 10
Lalai1
Medanvoice_setting.pitchJenisintegerKeperluanPilihanNilai & had
Minimum: -12
Maksimum: 12
Lalai0
Medanvoice_setting.emotionJenisstringKeperluanPilihanNilai & had
happy, sad, angry, fearful, disgusted, surprised, calm, fluent
Lalai—
Medanvoice_setting.text_normalizationJenisbooleanKeperluanPilihanNilai & hadLalaifalse
Medanvoice_setting.latex_readJenisbooleanKeperluanPilihanNilai & hadLalaifalse
Medanaudio_settingJenisobjectKeperluanPilihanNilai & hadLalai—
Medanaudio_setting.sample_rateJenisintegerKeperluanPilihanNilai & had
8,000, 16,000, 22,050, 24,000, 32,000, 44,100
Lalai32,000
Medanaudio_setting.bitrateJenisintegerKeperluanPilihanNilai & had
32,000, 64,000, 128,000, 256,000
Lalai128,000
Medanaudio_setting.formatJenisstringKeperluanPilihanNilai & had
mp3, pcm, flac, wav
Lalaimp3
Medanaudio_setting.channelJenisintegerKeperluanPilihanNilai & had
1, 2
Lalai1
Medanaudio_setting.force_cbrJenisbooleanKeperluanPilihanNilai & hadLalaifalse
Medanpronunciation_dictJenisobjectKeperluanPilihanNilai & hadLalai—
Medanpronunciation_dict.toneJenisarrayKeperluanPilihanNilai & hadLalai—
Medantimber_weightsJenisarrayKeperluanPilihanNilai & hadLalai—
Medanlanguage_boostJenisstringKeperluanPilihanNilai & had
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
Lalai—
Medanvoice_modifyJenisobjectKeperluanPilihanNilai & hadLalai—
Medanvoice_modify.pitchJenisintegerKeperluanPilihanNilai & had
-100, 100
Lalai—
Medanvoice_modify.intensityJenisintegerKeperluanPilihanNilai & had
-100, 100
Lalai—
Medanvoice_modify.timbreJenisintegerKeperluanPilihanNilai & had
-100, 100
Lalai—
Medanvoice_modify.sound_effectsJenisstringKeperluanPilihanNilai & had
spacious_echo, auditorium_echo, lofi_telephone, robotic
Lalai—
Medansubtitle_enableJenisbooleanKeperluanPilihanNilai & hadLalaifalse
Medanoutput_formatJenisstringKeperluanPilihanNilai & had
url, hex
Lalaihex
Medanaigc_watermarkJenisbooleanKeperluanPilihanNilai & hadLalaifalse
Parameter kaedah dan kitar hayat
ParameterKontrak
Parametercontent_typeKontrakapplication/json
ParameterrequiredKontrakmodel, text
ParameteroptionalKontrakstream, voice_setting, audio_setting, pronunciation_dict, timber_weights, language_boost, voice_modify, subtitle_enable, output_format, aigc_watermark
Parametermaterial_typesKontraktext
ParameterconditionsKontrakUse text, not input or contents. Fewer than 10000 Unicode characters; stream is false or omitted., PCM is raw audio with its returned sample geometry; do not invent a WAV header or bit depth.

Kitar hayat: synchronous_result_then_owned_library

GET /v1/media/assets

GET /v1/media/assets/{asset_id}

Pelan harga

Rujukan tarif tidak menambah pilihan permintaan. Parameter yang disokong disenaraikan untuk kaedah yang dipilih.

Mod pantas
Tidak dinyatakan Apabila mod pantas dipilih
Mod flex
Tidak dinyatakan Apabila mod flex dipilih
Usaha penaakulan maksimum
Tidak dinyatakan Apabila usaha penaakulan maksimum menggunakan pelarasan default

Kadar Ailoot

Harga mengikut konfigurasi

Padankan setiap caj dengan syarat yang dipaparkan. Gunakan satu kadar bagi setiap set konfigurasi alternatif.

KonfigurasiJadual kadarUnit pengebilanCaj
KonfigurasiKadar asas tokenJadual kadarKadar asasUnit pengebilan—Caj
Input · Token input — / 1K token
Output · Token output — / 1K token
Input · Bacaan cache — / 1K token
Input · Penulisan cache — / 1K token
Input · Penulisan cache, 1 jam — / 1K token
Konfigurasiaksara inputJadual kadar—Unit pengebilanbagi setiap aksara masukanCaj
Input · aksara input $0.00012 bagi setiap aksara masukan

Ailoot merizabkan anggaran amaun sebelum permintaan. Selepas hasil diterima, caj akhir diselesaikan berdasarkan penggunaan terukur. Penyelesaian caj penstriman menggunakan rekod penggunaan akhir. Cara rizab dan penyelesaian caj berfungsi →

Contoh permintaan

Ailoot Ultra · Speech

set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\nexport AILOOT_API_KEY\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "minimax/speech-2.6-turbo", "text": "Hello, this is a short speech example.", "stream": false, "output_format": "hex", "audio_setting": {"format": "mp3", "sample_rate": 32000, "channel": 1}}')\n\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/audio/speech \\\n  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\n# Submit once. Retain the complete result, original identifiers and every response header.\n

Terima dan simpan hasil

Ailoot Ultra · Speech

mp3,pcm,flac,wav

Simpan semua hasil yang selesai

Simpan setiap respons lengkap, fail dan bahagian kandungan yang dikembalikan.

Retain the full JSON. Decode every hex audio byte or use the returned owned URL. Keep the actual format, sample rate, channel count and usage_characters.

Jika respons asal perlu disemak

Preserve the original response, headers and X-Client-Request-ID. An uncertain outcome does not authorize another creation.

Medan respons
MedanJenis
Medandata.audioJenisstring
Medanextra_infoJenisobject
Medantrace_idJenisstring

Alias

Alias model

Ailoot Ultra minimax/speech-2.6-turbo

Alias laluan kaedah

Gunakan laluan kaedah yang dipaparkan di atas.

ID pemanggil berkaitan

minimax/speech-2.6-turbo

", "method_identity": { "effective_request_model_id": "minimax/speech-2.6-turbo", "fmt": "speech", "http": "POST", "path": "/v1/audio/speech", "request_model_id": "minimax/speech-2.6-turbo", "route_label": "Ultra" }, "method_key": "Ultra|speech|/v1/audio/speech|minimax%2Fspeech-2.6-turbo", "ordinal": 0, "rawMethod": { "available": null, "cache_read": null, "cache_write": null, "cache_write_1h": null, "contract": { "data": { "all_results": "Retain the complete response, all actual results, original identifiers, usage and response headers.", "authentication": { "api_key_source": "AILOOT_API_KEY", "header": "Authorization: Bearer" }, "example_body": { "audio_setting": { "channel": 1, "format": "mp3", "sample_rate": 32000 }, "model": "minimax/speech-2.6-turbo", "output_format": "hex", "stream": false, "text": "Hello, this is a short speech example." }, "lifecycle": { "assets": [ { "http": "GET", "path": "/v1/media/assets", "query": { "cursor": "actual returned next_cursor, when present", "family": "audio" } }, { "http": "GET", "path": "/v1/media/assets/{asset_id}" } ], "cancel_endpoint": null, "create": { "http": "POST", "path": "/v1/audio/speech" }, "mode": "synchronous_result_then_owned_library", "operation_id_is_not_task_id": true, "owned_content": { "http": "GET", "path": "/v1/media/assets/{asset_id}/content", "url_source": "Use the exact returned content_url. Refresh an expired link by reading the same existing asset." }, "status": [], "unknown": "Preserve the original response, headers and X-Client-Request-ID. An uncertain outcome does not authorize another creation.", "unknown_no_replay": true }, "outputs": { "all_results": "Retain the full JSON. Decode every hex audio byte or use the returned owned URL. Keep the actual format, sample rate, channel count and usage_characters.", "family": "audio", "fields": [ { "name": "data.audio", "type": "string" }, { "name": "extra_info", "type": "object" }, { "name": "trace_id", "type": "string" } ], "format": [ "mp3", "pcm", "flac", "wav" ] }, "parameters": [ { "default_known": false, "enum": [ "minimax/speech-2.6-turbo" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "default_known": false, "enum_known": false, "maxLength": 9999, "minLength": 1, "name": "text", "required": true, "type": "string" }, { "default": false, "default_known": true, "enum": [ false ], "enum_known": true, "name": "stream", "required": false, "type": "boolean" }, { "default_known": false, "enum_known": false, "name": "voice_setting", "properties": { "emotion": { "enum": [ "happy", "sad", "angry", "fearful", "disgusted", "surprised", "calm", "fluent" ], "type": "string" }, "latex_read": { "default": false, "type": "boolean" }, "pitch": { "default": 0, "maximum": 12, "minimum": -12, "type": "integer" }, "speed": { "default": 1, "maximum": 2, "minimum": 0.5, "type": "number" }, "text_normalization": { "default": false, "type": "boolean" }, "voice_id": { "type": "string" }, "vol": { "default": 1, "exclusiveMinimum": true, "maximum": 10, "minimum": 0, "type": "number" } }, "required": false, "type": "object" }, { "default_known": false, "enum_known": false, "name": "voice_setting.voice_id", "required": false, "type": "string" }, { "default": 1, "default_known": true, "enum_known": false, "maximum": 2, "minimum": 0.5, "name": "voice_setting.speed", "required": false, "type": "number" }, { "default": 1, "default_known": true, "enum_known": false, "exclusiveMinimum": true, "maximum": 10, "minimum": 0, "name": "voice_setting.vol", "required": false, "type": "number" }, { "default": 0, "default_known": true, "enum_known": false, "maximum": 12, "minimum": -12, "name": "voice_setting.pitch", "required": false, "type": "integer" }, { "default_known": false, "enum": [ "happy", "sad", "angry", "fearful", "disgusted", "surprised", "calm", "fluent" ], "enum_known": true, "name": "voice_setting.emotion", "required": false, "type": "string" }, { "default": false, "default_known": true, "enum_known": false, "name": "voice_setting.text_normalization", "required": false, "type": "boolean" }, { "default": false, "default_known": true, "enum_known": false, "name": "voice_setting.latex_read", "required": false, "type": "boolean" }, { "default_known": false, "enum_known": false, "name": "audio_setting", "properties": { "bitrate": { "default": 128000, "enum": [ 32000, 64000, 128000, 256000 ], "type": "integer" }, "channel": { "default": 1, "enum": [ 1, 2 ], "type": "integer" }, "force_cbr": { "default": false, "type": "boolean" }, "format": { "default": "mp3", "enum": [ "mp3", "pcm", "flac", "wav" ], "type": "string" }, "sample_rate": { "default": 32000, "enum": [ 8000, 16000, 22050, 24000, 32000, 44100 ], "type": "integer" } }, "required": false, "type": "object" }, { "default": 32000, "default_known": true, "enum": [ 8000, 16000, 22050, 24000, 32000, 44100 ], "enum_known": true, "name": "audio_setting.sample_rate", "required": false, "type": "integer" }, { "default": 128000, "default_known": true, "enum": [ 32000, 64000, 128000, 256000 ], "enum_known": true, "name": "audio_setting.bitrate", "required": false, "type": "integer" }, { "default": "mp3", "default_known": true, "enum": [ "mp3", "pcm", "flac", "wav" ], "enum_known": true, "name": "audio_setting.format", "required": false, "type": "string" }, { "default": 1, "default_known": true, "enum": [ 1, 2 ], "enum_known": true, "name": "audio_setting.channel", "required": false, "type": "integer" }, { "default": false, "default_known": true, "enum_known": false, "name": "audio_setting.force_cbr", "required": false, "type": "boolean" }, { "default_known": false, "enum_known": false, "name": "pronunciation_dict", "properties": { "tone": { "items": { "type": "string" }, "type": "array" } }, "required": false, "type": "object" }, { "default_known": false, "enum_known": false, "items": { "type": "string" }, "name": "pronunciation_dict.tone", "required": false, "type": "array" }, { "default_known": false, "enum_known": false, "items": { "properties": { "voice_id": { "type": "string" }, "weight": { "type": "integer" } }, "type": "object" }, "name": "timber_weights", "required": false, "type": "array" }, { "default_known": false, "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" ], "enum_known": true, "name": "language_boost", "required": false, "type": "string" }, { "default_known": false, "enum_known": false, "name": "voice_modify", "properties": { "intensity": { "enum": [ -100, 100 ], "type": "integer" }, "pitch": { "enum": [ -100, 100 ], "type": "integer" }, "sound_effects": { "enum": [ "spacious_echo", "auditorium_echo", "lofi_telephone", "robotic" ], "type": "string" }, "timbre": { "enum": [ -100, 100 ], "type": "integer" } }, "required": false, "type": "object" }, { "default_known": false, "enum": [ -100, 100 ], "enum_known": true, "name": "voice_modify.pitch", "required": false, "type": "integer" }, { "default_known": false, "enum": [ -100, 100 ], "enum_known": true, "name": "voice_modify.intensity", "required": false, "type": "integer" }, { "default_known": false, "enum": [ -100, 100 ], "enum_known": true, "name": "voice_modify.timbre", "required": false, "type": "integer" }, { "default_known": false, "enum": [ "spacious_echo", "auditorium_echo", "lofi_telephone", "robotic" ], "enum_known": true, "name": "voice_modify.sound_effects", "required": false, "type": "string" }, { "default": false, "default_known": true, "enum_known": false, "name": "subtitle_enable", "required": false, "type": "boolean" }, { "default": "hex", "default_known": true, "enum": [ "url", "hex" ], "enum_known": true, "name": "output_format", "required": false, "type": "string" }, { "default": false, "default_known": true, "enum_known": false, "name": "aigc_watermark", "required": false, "type": "boolean" } ], "request_schema": { "properties": { "aigc_watermark": { "default": false, "type": "boolean" }, "audio_setting": { "properties": { "bitrate": { "default": 128000, "enum": [ 32000, 64000, 128000, 256000 ], "type": "integer" }, "channel": { "default": 1, "enum": [ 1, 2 ], "type": "integer" }, "force_cbr": { "default": false, "type": "boolean" }, "format": { "default": "mp3", "enum": [ "mp3", "pcm", "flac", "wav" ], "type": "string" }, "sample_rate": { "default": 32000, "enum": [ 8000, 16000, 22050, 24000, 32000, 44100 ], "type": "integer" } }, "type": "object" }, "language_boost": { "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" ], "type": "string" }, "model": { "enum": [ "minimax/speech-2.6-turbo" ], "type": "string" }, "output_format": { "default": "hex", "enum": [ "url", "hex" ], "type": "string" }, "pronunciation_dict": { "properties": { "tone": { "items": { "type": "string" }, "type": "array" } }, "type": "object" }, "stream": { "default": false, "enum": [ false ], "type": "boolean" }, "subtitle_enable": { "default": false, "type": "boolean" }, "text": { "maxLength": 9999, "minLength": 1, "type": "string" }, "timber_weights": { "items": { "properties": { "voice_id": { "type": "string" }, "weight": { "type": "integer" } }, "type": "object" }, "type": "array" }, "voice_modify": { "properties": { "intensity": { "enum": [ -100, 100 ], "type": "integer" }, "pitch": { "enum": [ -100, 100 ], "type": "integer" }, "sound_effects": { "enum": [ "spacious_echo", "auditorium_echo", "lofi_telephone", "robotic" ], "type": "string" }, "timbre": { "enum": [ -100, 100 ], "type": "integer" } }, "type": "object" }, "voice_setting": { "properties": { "emotion": { "enum": [ "happy", "sad", "angry", "fearful", "disgusted", "surprised", "calm", "fluent" ], "type": "string" }, "latex_read": { "default": false, "type": "boolean" }, "pitch": { "default": 0, "maximum": 12, "minimum": -12, "type": "integer" }, "speed": { "default": 1, "maximum": 2, "minimum": 0.5, "type": "number" }, "text_normalization": { "default": false, "type": "boolean" }, "voice_id": { "type": "string" }, "vol": { "default": 1, "exclusiveMinimum": true, "maximum": 10, "minimum": 0, "type": "number" } }, "type": "object" } }, "required": [ "model", "text" ], "type": "object" }, "schema_template": { "body": { "audio_setting": { "channel": 1, "format": "mp3", "sample_rate": 32000 }, "model": "minimax/speech-2.6-turbo", "output_format": "hex", "stream": false, "text": "Hello, this is a short speech example." }, "content_type": "application/json" } }, "input": { "conditions": [ "Use text, not input or contents. Fewer than 10000 Unicode characters; stream is false or omitted.", "PCM is raw audio with its returned sample geometry; do not invent a WAV header or bit depth." ], "content_type": "application/json", "material_types": [ "text" ], "optional": [ "stream", "voice_setting", "audio_setting", "pronunciation_dict", "timber_weights", "language_boost", "voice_modify", "subtitle_enable", "output_format", "aigc_watermark" ], "required": [ "model", "text" ] }, "lifecycle": { "assets": [ { "http": "GET", "path": "/v1/media/assets", "query": { "cursor": "actual returned next_cursor, when present", "family": "audio" } }, { "http": "GET", "path": "/v1/media/assets/{asset_id}" } ], "cancel_endpoint": null, "create": { "http": "POST", "path": "/v1/audio/speech" }, "mode": "synchronous_result_then_owned_library", "operation_id_is_not_task_id": true, "owned_content": { "http": "GET", "path": "/v1/media/assets/{asset_id}/content", "url_source": "Use the exact returned content_url. Refresh an expired link by reading the same existing asset." }, "status": [], "unknown": "Preserve the original response, headers and X-Client-Request-ID. An uncertain outcome does not authorize another creation.", "unknown_no_replay": true }, "method": { "http": "POST", "path": "/v1/audio/speech" }, "method_aliases": [], "output": { "all_results": "Retain the full JSON. Decode every hex audio byte or use the returned owned URL. Keep the actual format, sample rate, channel count and usage_characters.", "family": "audio", "fields": [ { "name": "data.audio", "type": "string" }, { "name": "extra_info", "type": "object" }, { "name": "trace_id", "type": "string" } ], "format": [ "mp3", "pcm", "flac", "wav" ] } }, "ctx": null, "declared_pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] }, { "dimensions": { "quoted_unit": "per input character" }, "label": "input character", "units": [ { "amount": "0.00012", "amount_unit": "usd_per_exact_native_unit", "billing_input": true, "estimate_only": false, "key": "audio_input_character", "label": "input character", "native_amount_usd_per_unit": "0.00012", "native_quantity": 1, "public_unit_label": "per input character", "quantity": 1, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "audio_input_character" } ] } ], "examples": [ { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\nexport AILOOT_API_KEY\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"minimax/speech-2.6-turbo\", \"text\": \"Hello, this is a short speech example.\", \"stream\": false, \"output_format\": \"hex\", \"audio_setting\": {\"format\": \"mp3\", \"sample_rate\": 32000, \"channel\": 1}}')\n\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/audio/speech \\\n -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\n# Submit once. Retain the complete result, original identifiers and every response header.\n", "label": "curl · create once and retain the complete result", "language": "bash" } ], "family": "openai", "fast_multiplier": null, "flex_multiplier": null, "fmt": "speech", "http": "POST", "img_in": null, "img_out": null, "in": null, "input": [ "text" ], "label": "Speech", "max_out": null, "max_reasoning_effort_multiplier": null, "method_aliases": [], "out": null, "output": [ "audio" ], "path": "/v1/audio/speech", "price_conditions": [ { "label": "Fast mode", "value": "Not specified", "when": "When fast mode is selected" }, { "label": "Flex mode", "value": "Not specified", "when": "When flex mode is selected" }, { "label": "Maximum reasoning effort", "value": "Not specified", "when": "When maximum reasoning effort uses the default adjustment" } ], "pricing": { "billing_mode": "per_request", "cache_read_price": null, "cache_write_1h_price": null, "cache_write_price": null, "fast_multiplier": null, "flex_multiplier": null, "image_input_price": null, "image_output_price": null, "input_price": null, "intervals": null, "max_reasoning_effort_multiplier": null, "output_price": null, "per_request_price": null, "unit_prices": { "audio_input_character": "0.00012" } }, "pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] }, { "dimensions": { "quoted_unit": "per input character" }, "label": "input character", "units": [ { "amount": "0.00012", "amount_unit": "usd_per_exact_native_unit", "billing_input": true, "estimate_only": false, "key": "audio_input_character", "label": "input character", "native_amount_usd_per_unit": "0.00012", "native_quantity": 1, "public_unit_label": "per input character", "quantity": 1, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "audio_input_character" } ] } ], "request_model_id": "minimax/speech-2.6-turbo", "route_label": "Ultra", "status_reads": [], "tiers": [], "unit": "per_request", "units": [ { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" }, { "amount": "0.00012", "amount_unit": "usd_per_exact_native_unit", "billing_input": true, "estimate_only": false, "key": "audio_input_character", "label": "input character", "native_amount_usd_per_unit": "0.00012", "native_quantity": 1, "public_unit_label": "per input character", "quantity": 1, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "audio_input_character" } ] } } ], "model_id": "minimax/speech-2.6-turbo", "nativeProvenance": { "input_facts_canonical_sha256": "33b3b10bbd79af20e246dd85646b73b9298fa9123d398c62134756739528755e", "input_html_sha256": "48fa70b0a6597662efca51a91542a912d45d7e667b3eb6a79beb7f112fb60333", "private_audit_sha256": "ff776c63c59448e9cc5ea233f5c4f18f885e1b24a5e5b5b3d0e98417f063a1a0", "role": "historical-normalized-input-audit-hashes", "schema": "ailoot-native-model-provenance-v2" }, "page": { "canonical": "https://ailoot.ai/models/ms/minimax-speech-2-6-turbo/", "description": "Speech 2.6 Turbo ialah model teks-ke-pertuturan MiniMax untuk mengubah skrip yang telah siap menjadi audio. Edisi minimax/speech-2.6-turbo menyediakan kawalan suara, penyampaian dan format audio, dengan balasan JSON lengkap serta pilihan output audio URL atau perenambelasan. Gunakannya untuk mencipta versi lisan mesej, pelajaran pendek atau skrip aplikasi yang dibekalkan.", "locale": "ms", "md_url": "https://ailoot.ai/models/ms/minimax-speech-2-6-turbo/index.md", "title": "MiniMax: Speech 2.6 Turbo — Ailoot", "url": "https://ailoot.ai/models/ms/minimax-speech-2-6-turbo/" }, "rawModel": { "about": "Speech 2.6 Turbo ialah edisi pertuturan MiniMax tepat yang dipilih oleh model: \"minimax/speech-2.6-turbo\". Gunakan POST /v1/audio/speech dengan badan application/json yang mengandungi model dan text untuk dituturkan. Inputnya ialah skrip bertulis dan hasilnya ialah audio sintesis. Untuk mesej aplikasi, bekalkan perkataan tepat yang perlu didengar oleh pendengar dan eja penuh sebarang singkatan yang kabur. Untuk pelajaran pendek, asingkan penerangan daripada contoh dalam skrip itu sendiri. Untuk aliran antara muka bernarasi, kaitkan setiap segmen lisan dengan tindakan pengguna yang khusus dan simpan skrip bersama audionya.\n\nMedan text mestilah tidak kosong dan mengandungi kurang daripada 10,000 aksara Unicode. Hantar skrip lisan lengkap dengan stream:false, atau jangan sertakan stream. Bahagikan bahan yang lebih panjang kepada segmen skrip lengkap yang berasingan sebelum menyerahkan setiap segmen. Dokumen boleh digunakan dengan membaca kandungan sebenarnya dan meletakkan petikan yang berkaitan dalam text; URL dokumen bukan pengganti skrip.\n\nPilih suara melalui voice_setting.voice_id. Kategori suara yang didokumenkan merangkumi suara sistem serta suara yang telah diklon atau direka melalui teks; gunakan ID suara yang sah untuk kategori yang dipilih. Suara contoh ialah audiobook_male_1. Objek yang sama mengawal speed dari 0.5 hingga 2, vol melebihi 0 hingga 10, dan pitch integer dari -12 hingga 12. Nilai lalainya ialah 1, 1 dan 0. Kawalan ini melaraskan aspek penyampaian lisan yang berbeza, jadi pilih secara berasingan dan bukannya meletakkan namanya dalam skrip.\n\nvoice_setting.emotion menerima happy, sad, angry, fearful, disgusted, surprised, calm dan fluent. Dokumentasi turut menerangkan pemadanan emosi secara automatik daripada teks. Untuk skrip yang banyak nombor, voice_setting.text_normalization mengaktifkan penormalan teks bahasa Cina dan Inggeris serta mempunyai nilai lalai false. voice_setting.latex_read mengawal bacaan ungkapan LaTeX dan turut mempunyai nilai lalai false. pronunciation_dict.tone ialah tatasusunan rentetan peraturan sebutan. Contoh yang diterbitkan ialah [\"草地/(cao3)(di1)\"]; kekalkan perkataan, garis miring dan struktur sebutan dalam kurungan apabila membekalkan peraturan.\n\naudio_setting.format menerima mp3, pcm, flac dan wav, dengan mp3 sebagai nilai lalai. sample_rate menerima 8000, 16000, 22050, 24000, 32000 dan 44100 Hz; nilai lalainya ialah 32000. channel ialah 1 untuk mono atau 2 untuk dua saluran, dengan nilai lalai 1. Nilai bitrate ialah 32000, 64000, 128000 dan 256000 bit sesaat, dengan nilai lalai 128000, dan terpakai pada mp3. Pilih pengekodan yang diperlukan oleh pemain atau alat penyuntingan yang akan menggunakan hasil.\n\nlanguage_boost ialah rentetan pilihan dan mempunyai nilai lalai null. Nilai yang dibenarkan ialah 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 dan auto. \"Chinese,Yue\" ialah satu nilai. Ia ialah kawalan yang berasingan daripada skrip dan ID suara. Skema turut menyediakan timber_weights untuk senarai pasangan voice_id dan weight integer, dengan setiap weight dari 1 hingga 100. Kekalkan ejaan parameter timber_weights semasa menyediakan permintaan. voice_modify.sound_effects ialah rentetan pilihan dengan nilai spacious_echo, auditorium_echo, lofi_telephone dan robotic.\n\nNilai lalai stream ialah false. Untuk balasan lengkap, output_format memilih url atau hex dan mempunyai nilai lalai hex. Dalam hasil JSON yang didokumenkan, data.audio membawa perwakilan yang dipilih: muat turun URL Ailoot bertandatangan yang lengkap, termasuk rentetan pertanyaannya, atau nyahkod audio perenambelasan yang lengkap menjadi bait. Simpan hasil asal bersama data.status, base_resp, trace_id dan extra_info, yang merangkumi format audio sebenar, kadar sampel, bilangan saluran, saiz dan usage_characters.\n\nsubtitle_enable ialah boolean yang mempunyai nilai lalai false dan terpakai pada output tanpa penstriman. aigc_watermark ialah boolean yang mempunyai nilai lalai false dan mengawal penanda irama yang boleh didengar pada hujung audio terjana. Simpan setiap hasil audio atau sari kata yang dikembalikan, dan semak sebutan, nombor serta fail yang telah siap sebelum meletakkannya dalam aplikasi. Jika penghantaran tidak pasti, simpan pengecam permintaan asal dan balasan untuk menyemak percubaan sedia ada. Ailoot turut menyimpan audio yang telah siap dalam pustaka media anda. Dengan output_format:\"url\", data.audio mengandungi pautan bertandatangan ke aset yang disimpan itu; ID aset muncul dalam laluan /v1/media/assets/{asset_id}/content. Pautan fail Ailoot bertandatangan sah selama 24 jam dari masa dikeluarkan. Gunakan kunci API yang sama untuk GET /v1/media/assets?family=audio dan ikuti setiap next_cursor untuk mencari rekod aset audio. Baca GET /v1/media/assets/{asset_id} bagi setiap rekod yang dipilih dan muat turun content_url tepatnya, termasuk rentetan pertanyaan. Jika permintaan fail mengembalikan 404 dengan kod link_expired, baca semula aset yang sama untuk mendapatkan content_url yang diperbaharui. Perbaharui hasil yang disimpan dan bukannya menjana audio semula untuk menggantikan pautan luput.", "alias_of": null, "aliases": [], "author": "MiniMax", "ctx": null, "formats": [ "speech" ], "id": "minimax/speech-2.6-turbo", "input": [ "text" ], "kind": "speech", "max_out": null, "methods": [ { "available": null, "cache_read": null, "cache_write": null, "cache_write_1h": null, "contract": { "data": { "all_results": "Retain the complete response, all actual results, original identifiers, usage and response headers.", "authentication": { "api_key_source": "AILOOT_API_KEY", "header": "Authorization: Bearer" }, "example_body": { "audio_setting": { "channel": 1, "format": "mp3", "sample_rate": 32000 }, "model": "minimax/speech-2.6-turbo", "output_format": "hex", "stream": false, "text": "Hello, this is a short speech example." }, "lifecycle": { "assets": [ { "http": "GET", "path": "/v1/media/assets", "query": { "cursor": "actual returned next_cursor, when present", "family": "audio" } }, { "http": "GET", "path": "/v1/media/assets/{asset_id}" } ], "cancel_endpoint": null, "create": { "http": "POST", "path": "/v1/audio/speech" }, "mode": "synchronous_result_then_owned_library", "operation_id_is_not_task_id": true, "owned_content": { "http": "GET", "path": "/v1/media/assets/{asset_id}/content", "url_source": "Use the exact returned content_url. Refresh an expired link by reading the same existing asset." }, "status": [], "unknown": "Preserve the original response, headers and X-Client-Request-ID. An uncertain outcome does not authorize another creation.", "unknown_no_replay": true }, "outputs": { "all_results": "Retain the full JSON. Decode every hex audio byte or use the returned owned URL. Keep the actual format, sample rate, channel count and usage_characters.", "family": "audio", "fields": [ { "name": "data.audio", "type": "string" }, { "name": "extra_info", "type": "object" }, { "name": "trace_id", "type": "string" } ], "format": [ "mp3", "pcm", "flac", "wav" ] }, "parameters": [ { "default_known": false, "enum": [ "minimax/speech-2.6-turbo" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "default_known": false, "enum_known": false, "maxLength": 9999, "minLength": 1, "name": "text", "required": true, "type": "string" }, { "default": false, "default_known": true, "enum": [ false ], "enum_known": true, "name": "stream", "required": false, "type": "boolean" }, { "default_known": false, "enum_known": false, "name": "voice_setting", "properties": { "emotion": { "enum": [ "happy", "sad", "angry", "fearful", "disgusted", "surprised", "calm", "fluent" ], "type": "string" }, "latex_read": { "default": false, "type": "boolean" }, "pitch": { "default": 0, "maximum": 12, "minimum": -12, "type": "integer" }, "speed": { "default": 1, "maximum": 2, "minimum": 0.5, "type": "number" }, "text_normalization": { "default": false, "type": "boolean" }, "voice_id": { "type": "string" }, "vol": { "default": 1, "exclusiveMinimum": true, "maximum": 10, "minimum": 0, "type": "number" } }, "required": false, "type": "object" }, { "default_known": false, "enum_known": false, "name": "voice_setting.voice_id", "required": false, "type": "string" }, { "default": 1, "default_known": true, "enum_known": false, "maximum": 2, "minimum": 0.5, "name": "voice_setting.speed", "required": false, "type": "number" }, { "default": 1, "default_known": true, "enum_known": false, "exclusiveMinimum": true, "maximum": 10, "minimum": 0, "name": "voice_setting.vol", "required": false, "type": "number" }, { "default": 0, "default_known": true, "enum_known": false, "maximum": 12, "minimum": -12, "name": "voice_setting.pitch", "required": false, "type": "integer" }, { "default_known": false, "enum": [ "happy", "sad", "angry", "fearful", "disgusted", "surprised", "calm", "fluent" ], "enum_known": true, "name": "voice_setting.emotion", "required": false, "type": "string" }, { "default": false, "default_known": true, "enum_known": false, "name": "voice_setting.text_normalization", "required": false, "type": "boolean" }, { "default": false, "default_known": true, "enum_known": false, "name": "voice_setting.latex_read", "required": false, "type": "boolean" }, { "default_known": false, "enum_known": false, "name": "audio_setting", "properties": { "bitrate": { "default": 128000, "enum": [ 32000, 64000, 128000, 256000 ], "type": "integer" }, "channel": { "default": 1, "enum": [ 1, 2 ], "type": "integer" }, "force_cbr": { "default": false, "type": "boolean" }, "format": { "default": "mp3", "enum": [ "mp3", "pcm", "flac", "wav" ], "type": "string" }, "sample_rate": { "default": 32000, "enum": [ 8000, 16000, 22050, 24000, 32000, 44100 ], "type": "integer" } }, "required": false, "type": "object" }, { "default": 32000, "default_known": true, "enum": [ 8000, 16000, 22050, 24000, 32000, 44100 ], "enum_known": true, "name": "audio_setting.sample_rate", "required": false, "type": "integer" }, { "default": 128000, "default_known": true, "enum": [ 32000, 64000, 128000, 256000 ], "enum_known": true, "name": "audio_setting.bitrate", "required": false, "type": "integer" }, { "default": "mp3", "default_known": true, "enum": [ "mp3", "pcm", "flac", "wav" ], "enum_known": true, "name": "audio_setting.format", "required": false, "type": "string" }, { "default": 1, "default_known": true, "enum": [ 1, 2 ], "enum_known": true, "name": "audio_setting.channel", "required": false, "type": "integer" }, { "default": false, "default_known": true, "enum_known": false, "name": "audio_setting.force_cbr", "required": false, "type": "boolean" }, { "default_known": false, "enum_known": false, "name": "pronunciation_dict", "properties": { "tone": { "items": { "type": "string" }, "type": "array" } }, "required": false, "type": "object" }, { "default_known": false, "enum_known": false, "items": { "type": "string" }, "name": "pronunciation_dict.tone", "required": false, "type": "array" }, { "default_known": false, "enum_known": false, "items": { "properties": { "voice_id": { "type": "string" }, "weight": { "type": "integer" } }, "type": "object" }, "name": "timber_weights", "required": false, "type": "array" }, { "default_known": false, "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" ], "enum_known": true, "name": "language_boost", "required": false, "type": "string" }, { "default_known": false, "enum_known": false, "name": "voice_modify", "properties": { "intensity": { "enum": [ -100, 100 ], "type": "integer" }, "pitch": { "enum": [ -100, 100 ], "type": "integer" }, "sound_effects": { "enum": [ "spacious_echo", "auditorium_echo", "lofi_telephone", "robotic" ], "type": "string" }, "timbre": { "enum": [ -100, 100 ], "type": "integer" } }, "required": false, "type": "object" }, { "default_known": false, "enum": [ -100, 100 ], "enum_known": true, "name": "voice_modify.pitch", "required": false, "type": "integer" }, { "default_known": false, "enum": [ -100, 100 ], "enum_known": true, "name": "voice_modify.intensity", "required": false, "type": "integer" }, { "default_known": false, "enum": [ -100, 100 ], "enum_known": true, "name": "voice_modify.timbre", "required": false, "type": "integer" }, { "default_known": false, "enum": [ "spacious_echo", "auditorium_echo", "lofi_telephone", "robotic" ], "enum_known": true, "name": "voice_modify.sound_effects", "required": false, "type": "string" }, { "default": false, "default_known": true, "enum_known": false, "name": "subtitle_enable", "required": false, "type": "boolean" }, { "default": "hex", "default_known": true, "enum": [ "url", "hex" ], "enum_known": true, "name": "output_format", "required": false, "type": "string" }, { "default": false, "default_known": true, "enum_known": false, "name": "aigc_watermark", "required": false, "type": "boolean" } ], "request_schema": { "properties": { "aigc_watermark": { "default": false, "type": "boolean" }, "audio_setting": { "properties": { "bitrate": { "default": 128000, "enum": [ 32000, 64000, 128000, 256000 ], "type": "integer" }, "channel": { "default": 1, "enum": [ 1, 2 ], "type": "integer" }, "force_cbr": { "default": false, "type": "boolean" }, "format": { "default": "mp3", "enum": [ "mp3", "pcm", "flac", "wav" ], "type": "string" }, "sample_rate": { "default": 32000, "enum": [ 8000, 16000, 22050, 24000, 32000, 44100 ], "type": "integer" } }, "type": "object" }, "language_boost": { "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" ], "type": "string" }, "model": { "enum": [ "minimax/speech-2.6-turbo" ], "type": "string" }, "output_format": { "default": "hex", "enum": [ "url", "hex" ], "type": "string" }, "pronunciation_dict": { "properties": { "tone": { "items": { "type": "string" }, "type": "array" } }, "type": "object" }, "stream": { "default": false, "enum": [ false ], "type": "boolean" }, "subtitle_enable": { "default": false, "type": "boolean" }, "text": { "maxLength": 9999, "minLength": 1, "type": "string" }, "timber_weights": { "items": { "properties": { "voice_id": { "type": "string" }, "weight": { "type": "integer" } }, "type": "object" }, "type": "array" }, "voice_modify": { "properties": { "intensity": { "enum": [ -100, 100 ], "type": "integer" }, "pitch": { "enum": [ -100, 100 ], "type": "integer" }, "sound_effects": { "enum": [ "spacious_echo", "auditorium_echo", "lofi_telephone", "robotic" ], "type": "string" }, "timbre": { "enum": [ -100, 100 ], "type": "integer" } }, "type": "object" }, "voice_setting": { "properties": { "emotion": { "enum": [ "happy", "sad", "angry", "fearful", "disgusted", "surprised", "calm", "fluent" ], "type": "string" }, "latex_read": { "default": false, "type": "boolean" }, "pitch": { "default": 0, "maximum": 12, "minimum": -12, "type": "integer" }, "speed": { "default": 1, "maximum": 2, "minimum": 0.5, "type": "number" }, "text_normalization": { "default": false, "type": "boolean" }, "voice_id": { "type": "string" }, "vol": { "default": 1, "exclusiveMinimum": true, "maximum": 10, "minimum": 0, "type": "number" } }, "type": "object" } }, "required": [ "model", "text" ], "type": "object" }, "schema_template": { "body": { "audio_setting": { "channel": 1, "format": "mp3", "sample_rate": 32000 }, "model": "minimax/speech-2.6-turbo", "output_format": "hex", "stream": false, "text": "Hello, this is a short speech example." }, "content_type": "application/json" } }, "input": { "conditions": [ "Use text, not input or contents. Fewer than 10000 Unicode characters; stream is false or omitted.", "PCM is raw audio with its returned sample geometry; do not invent a WAV header or bit depth." ], "content_type": "application/json", "material_types": [ "text" ], "optional": [ "stream", "voice_setting", "audio_setting", "pronunciation_dict", "timber_weights", "language_boost", "voice_modify", "subtitle_enable", "output_format", "aigc_watermark" ], "required": [ "model", "text" ] }, "lifecycle": { "assets": [ { "http": "GET", "path": "/v1/media/assets", "query": { "cursor": "actual returned next_cursor, when present", "family": "audio" } }, { "http": "GET", "path": "/v1/media/assets/{asset_id}" } ], "cancel_endpoint": null, "create": { "http": "POST", "path": "/v1/audio/speech" }, "mode": "synchronous_result_then_owned_library", "operation_id_is_not_task_id": true, "owned_content": { "http": "GET", "path": "/v1/media/assets/{asset_id}/content", "url_source": "Use the exact returned content_url. Refresh an expired link by reading the same existing asset." }, "status": [], "unknown": "Preserve the original response, headers and X-Client-Request-ID. An uncertain outcome does not authorize another creation.", "unknown_no_replay": true }, "method": { "http": "POST", "path": "/v1/audio/speech" }, "method_aliases": [], "output": { "all_results": "Retain the full JSON. Decode every hex audio byte or use the returned owned URL. Keep the actual format, sample rate, channel count and usage_characters.", "family": "audio", "fields": [ { "name": "data.audio", "type": "string" }, { "name": "extra_info", "type": "object" }, { "name": "trace_id", "type": "string" } ], "format": [ "mp3", "pcm", "flac", "wav" ] } }, "ctx": null, "declared_pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] }, { "dimensions": { "quoted_unit": "per input character" }, "label": "input character", "units": [ { "amount": "0.00012", "amount_unit": "usd_per_exact_native_unit", "billing_input": true, "estimate_only": false, "key": "audio_input_character", "label": "input character", "native_amount_usd_per_unit": "0.00012", "native_quantity": 1, "public_unit_label": "per input character", "quantity": 1, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "audio_input_character" } ] } ], "examples": [ { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\nexport AILOOT_API_KEY\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"minimax/speech-2.6-turbo\", \"text\": \"Hello, this is a short speech example.\", \"stream\": false, \"output_format\": \"hex\", \"audio_setting\": {\"format\": \"mp3\", \"sample_rate\": 32000, \"channel\": 1}}')\n\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/audio/speech \\\n -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\n# Submit once. Retain the complete result, original identifiers and every response header.\n", "label": "curl · create once and retain the complete result", "language": "bash" } ], "family": "openai", "fast_multiplier": null, "flex_multiplier": null, "fmt": "speech", "http": "POST", "img_in": null, "img_out": null, "in": null, "input": [ "text" ], "label": "Speech", "max_out": null, "max_reasoning_effort_multiplier": null, "method_aliases": [], "out": null, "output": [ "audio" ], "path": "/v1/audio/speech", "price_conditions": [ { "label": "Fast mode", "value": "Not specified", "when": "When fast mode is selected" }, { "label": "Flex mode", "value": "Not specified", "when": "When flex mode is selected" }, { "label": "Maximum reasoning effort", "value": "Not specified", "when": "When maximum reasoning effort uses the default adjustment" } ], "pricing": { "billing_mode": "per_request", "cache_read_price": null, "cache_write_1h_price": null, "cache_write_price": null, "fast_multiplier": null, "flex_multiplier": null, "image_input_price": null, "image_output_price": null, "input_price": null, "intervals": null, "max_reasoning_effort_multiplier": null, "output_price": null, "per_request_price": null, "unit_prices": { "audio_input_character": "0.00012" } }, "pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] }, { "dimensions": { "quoted_unit": "per input character" }, "label": "input character", "units": [ { "amount": "0.00012", "amount_unit": "usd_per_exact_native_unit", "billing_input": true, "estimate_only": false, "key": "audio_input_character", "label": "input character", "native_amount_usd_per_unit": "0.00012", "native_quantity": 1, "public_unit_label": "per input character", "quantity": 1, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "audio_input_character" } ] } ], "request_model_id": "minimax/speech-2.6-turbo", "route_label": "Ultra", "status_reads": [], "tiers": [], "unit": "per_request", "units": [ { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" }, { "amount": "0.00012", "amount_unit": "usd_per_exact_native_unit", "billing_input": true, "estimate_only": false, "key": "audio_input_character", "label": "input character", "native_amount_usd_per_unit": "0.00012", "native_quantity": 1, "public_unit_label": "per input character", "quantity": 1, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "audio_input_character" } ] } ], "model_aliases": [ { "canonical_model_id": "minimax/speech-2.6-turbo", "request_model_id": "minimax/speech-2.6-turbo", "route_label": "Ultra" } ], "name": "MiniMax: Speech 2.6 Turbo", "price": { "in": "0.00012", "in_label": "per input character", "out": null, "out_label": null, "sort_in": null, "sort_out": null, "varies": false }, "short": "Speech 2.6 Turbo ialah model teks-ke-pertuturan MiniMax untuk mengubah skrip yang telah siap menjadi audio. Edisi minimax/speech-2.6-turbo menyediakan kawalan suara, penyampaian dan format audio, dengan balasan JSON lengkap serta pilihan output audio URL atau perenambelasan. Gunakannya untuk mencipta versi lisan mesej, pelajaran pendek atau skrip aplikasi yang dibekalkan." }, "renderer_schema": { "method_order": "Original DTO methods order; every exact route/format/path/caller survives.", "prices": "Original public DTO fields and original native display HTML; no flattened or normalized offers." }, "representation": "exact-public-dto-and-native-renderer-html", "representationNotes": { "current_reference": { "about_json_pointer": "/aboutHtml", "methods": [ { "contract_json_pointer": "/methods/0/rawMethod/contract", "html_json_pointer": "/methods/0/html", "method_ordinal": 0 } ], "role": "current-semantic-reference" }, "raw_input": { "examples_role": "historical-input-not-current-ready-examples", "json_pointers": [ "/rawModel", "/methods/0/rawMethod" ], "role": "historical-owner-input" }, "schema": "ailoot-native-model-representations-v1" }, "schema": "ailoot-static-model-facts-v1", "schema_version": 1, "shortText": "Speech 2.6 Turbo ialah model teks-ke-pertuturan MiniMax untuk mengubah skrip yang telah siap menjadi audio. Edisi minimax/speech-2.6-turbo menyediakan kawalan suara, penyampaian dan format audio, dengan balasan JSON lengkap serta pilihan output audio URL atau perenambelasan. Gunakannya untuk mencipta versi lisan mesej, pelajaran pendek atau skrip aplikasi yang dibekalkan.", "source": { "audit_sha256": "2e00086bcbfc28e64d0cebe97aa47c17d8d5618963027f8ffb9dc6123d7d25b1", "bridge_map_sha256": "1125275768b9636fc8461bc7da5061239a81ddfe508e2557843ca42c58ab0036", "raw_model_json_sha256": "0997245fea336be58fed5491b29bb2f7229807969abe40fb8d9c1e49516721f0", "renderer_sha256": "1dab5ba62521e9568c8b7c82005622cabbf330a075df7cce1f83274a04009460" }, "sourceRevision": "58b74056440df1e63c5e19ac46eabbe46008e38bc7fda34f1394609c00f1f0ff" }