Lapor cacat / pitakon fiturLapor cacat / pitakon fitur
Kloning swara Pengganti swara Narator Dubbing AI AI Voice Chat Rekayasa swara Generasi swara Celebrity Pencipta Karakter lan Suara Tambahan →

AI Voice - Sesame CSM-1B

Komersial Model 581 Ora ana tandha banyu Ora perlu mlebu
Model:
+ GPT-5, Claude, Gemini
Mesin TTS Self-hosted Apache 2.0
Sesame CSM-1B — Sesame CSM-1B - Apache 2.0. Conversational Speech Model designed for low-latency, real-time voice. 24 kHz output, sounds best with a short reference-audio context turn. Self-hosted on Free.ai for the /voice/realtime/ tool.
0 aksara ~0 token
Skala biaya karo angka aksara
Ngembangaké basa...

Apa Sesame CSM-1B Apa swarané kaya?

Sesame CSM-1B - Apache 2.0. Conversational Speech Model designed for low-latency, real-time voice. 24 kHz output, sounds best with a short reference-audio context turn. Self-hosted on Free.ai for the /voice/realtime/ tool.

Ing basa Inggris, tembung "hello" punika dipun-ginakaken kanggé nyebut tiyang ingkang sampun nyambut damel ing kantor, lan "hello" punika dipun-ginakaken kanggé nyebut tiyang ingkang sampun nyambut damel ing kantor.

Nalika gunakake Sesame CSM-1B

Buku Audio

Narrasi kanthi wujud panjang kanthi nada kang konsisten. Tetep bab-bab ing wektu, ngundhuh minangka WAV utawa MP3, lan stitch eksternal.

Podcast intros

Bukak bumper cekak lan ad-reads. Atur kecepatan kanggo energi, format-switching kanggo MP3 kanggo file cilik.

IVR + pesen suara

Prompt sistem telpon. Output kualitas studio tanpa booking, rekaman, utawa NDAs karo talenta swara.

Kacepetan

Tambah audio bebarengan karo isi ditulis kanggo para pamiarsa kang ora bisa maca lan dyslexic. Drop-in ing kaca apa wae.

Frasa conto

"Welcome to the show, today we are exploring the future of AI."
"Your package has arrived. Please retrieve it from the front desk."
"Once upon a time, in a quiet village far away, lived a curious child."
"Press one for sales, two for support, or stay on the line for an agent."
"Breaking news: scientists have discovered a new species of deep-sea fish."
"Thank you for choosing us. We appreciate your business and look forward to serving you again."

Pricing

Self-hosted on our GPUs. Generation draws from your daily free pool first; once that runs out, paid token packs start at $5 → 200,000 tokens. About ~5token per character, minimum 100 per clip.

Referensi model lengkap → · Lihat kabeh swara TTS → · Ngbandingaken2suara kang padha-padha →

Opsi Kaluwihan
Hasil
Kabupatèn Malang. Njupuk Token Tambahan
Kénging hasil sing luwih apik? Model Premium (GPT-5, Claude, Gemini) deliver higher quality. Papan

❤️ Love Free.ai? Nyathet kanca-kancamu!

Sign up kanggo njaluk link referral lan entuk 25,000 token per kanca.

Ingkang langkung? Ing taun 2000, cacahé wis tekan 30.000.
Daftar

Nglakoni panjalukmu...

Sesame CSM-1B - Apache 2.0. Conversational Speech Model designed for low-latency, real-time voice. 24 kHz output, sounds best with a short reference-audio …

Cara Nggunakake AI Voice - Sesame CSM-1B

1
Ngetik inputmu

Ngetik teks, ngundhuh file, utawa nyritakaké apa sing sampeyan karep. Ora ana akun sing dibutuhaké.

2
Klik kanggo nyipta

Ing jaman biyèn, para ahli nganggep yèn wangun-wangun iki paling apik.

3
Muter- unduh lan bagéan

Muter-muter, salinan, utawa share asilmu. Bebas kanggo pribadi lan komersial.

Gunake alat iki liwat API

Otomatisasi piranti iki saka kode dhewe. OpenAI-kompatibel REST endpoint, Bearer-token auth, ora ekstra SDK dibutuhaké. Token biaya match the web interface.

Dokumen Njupuk Kunci API 
curl -X POST https://api.free.ai/v1/tts/ \
  -H "Authorization: Bearer sk-free-..." \
  -H "Content-Type: application/json" \
  -d '{"text": "Hello from Free.ai", "voice": "af_heart", "model": "kokoro"}'

Free AI Tools

Kloning swara
Pengganti swara
Narator
Dubbing AI
AI Voice Chat
Rekayasa swara
Generasi swara Celebrity
Pencipta Karakter lan Suara

AI Voice - Sesame CSM-1B - FAQ

Sesame CSM-1B supports a wide range of languages. The exact list depends on the engine; the form on this page accepts any text and the engine will render in its supported languages. See /voice/ for the full multi-engine picker if you need a specific language.

Kabèh mesin ngasilaké basa Inggris Amerika kang neutral kanthi pigura lan aksen sing cocog karo wewengkon kanggo basa non-Inggris. Mesin Premium bisa ngasilaké variasi aksen - tempel conto kanggo ngbandingaké.

Dukungan SSML béda-béda miturut enjin. Tag paugeran, prosodi, lan pangétang dihormati ing akèh enjin premium lan ing sawetara sing dihost. Teks biasa tansah kerja - ora perlu markup.

Streaming TTS ana ing mesin premium liwat /v1/tts/ API endpoint karo stream=true. UI web ing kaca iki bakal bali klip lengkap sawisé rendering rampung.

Sesame CSM-1B dijalanaké ing GPUs kita dhewe. Generasi dijupuk saka pool gratis saben dinane. Sawisé dibuwang, token dibayar wiwit $5 → 200,000 token. Kira-kira ~5 token saben karakter, paling ora 100 saben klip.

Up to 5,000 characters per request on the web UI. For longer pieces (audiobooks, full chapters), use /voice/audiobook/ which chunks and stitches automatically, or call the API in a loop.

Yes - POST a list of strings to /v1/tts/batch/, or use the workspace UI at /workspace/ to chain TTS into a longer pipeline (e.g., translate → speak → stitch).

Ya - POST teks ka /v1/tts/ kaliyan model="Sesame CSM-1B" (utawa slug ing kaca iki). Kembali WAV utawa MP3. Lihat /api/ kanggé referensi lengkap + snippet SDK.

Halaman iki ya iku teks-ka-ucapan, ora kloning swara - swara iku standar mesin. Kanggo kloning swara (unggah audio referensi), tingali /voice/clone/, kang mbutuhaké sampeyan duwé hak swara utawa duwé persetujuan tertulis eksplisit.

Enjin kang dihost-aké dhéwé-dhéwé dioperasikaké ing GPU kang diduwèni Free.ai; ora ana sing ninggalake server kita. Enjin Premium nyedhiyani teks menyang penyedia model upstream ing ngisor DPA kita. Kita ora nglatih ing inputmu lan ora adol data.

Ya - Free.ai nyedhiyani panggunaan komersial audio kang dihasilaké. Lisénsi ing ngisor iki mesin (Apache 2.0, MIT, utawa syarat vendor) ditampilaké ing ndhuwur lan ing kaca referensi model; ing praktek iki tegesé voiceover, iklan, podcast, lan aplikasi kabèh ana ing njero skop.

Ya - tugas kang gagal di-refund kanthi otomatis menyang sumber (pool saben dina utawa token sing dibayar). Yen refund ora katon ing dina sing padha, kirim email contact@free.ai.

Ing taun 2000, cacahé wis tekan 30.000.

Akun

Ora ana kartu kredit sing dibutuhake

Kepiye sampeyan bisa ngukur alat iki?

4.6/5 from 5 ratings

Love Free.ai? Nyathet kanca-kancamu!