SLNG-hosted models use the
slng/ prefix in the model identifier. They are optimized for low latency in specific regions and billed through your SLNG account with no separate provider account needed.Text-to-Speech
Rime Arcana v3
Rime Arcana v3
Provider: Rime | Hosting: SLNG | Languages: English, HindiNatural prosody with improved voice quality over v1. French and Spanish support planned.
Best for: conversational agents, high-quality voice output.
Rime Arcana v1
Rime Arcana v1
Provider: Rime | Hosting: SLNG | Languages: Arabic, English, French, German, Spanish150+ voices across 5 languages. Uses unversioned identifiers (
arcana: instead of arcana:3-).Best for: broad language coverage, high-volume production.
Deepgram Aura 2
Deepgram Aura 2
Provider: Deepgram | Hosting: SLNG + Deepgram | Languages: English, SpanishAvailable both SLNG-hosted (low latency) and proxied to Deepgram (more languages). The
model field is required to pick a voice; there is no default.Best for: low-latency voice apps, multilingual IVR.
Cartesia Sonic 3
Cartesia Sonic 3
Provider: Cartesia | Hosting: Cartesia | Languages: 40+Streaming TTS with controls for speed, volume, and emotion.
Best for: real-time voice agents, expressive multilingual output.
Murf Falcon
Murf Falcon
Provider: Murf | Hosting: Murf | Languages: 16 localesReal-time multilingual TTS over WebSocket with multiple encodings and sample rates.
Best for: low-cost voice agents, IVR, assistants.
KugelAudio Kugel
KugelAudio Kugel
Provider: KugelAudio | Hosting: KugelAudio | Languages: 2687 voices with expressiveness control across 26 languages. Three variants trade off latency and quality.
Best for: multilingual voice agents, content creation.
Soniox TTS v1
Soniox TTS v1
Provider: Soniox | Hosting: Soniox | Languages: 50+Streaming and one-shot synthesis across 50+ languages.
Best for: multilingual streaming, long-form synthesis.
Sarvam Bulbul v3
Sarvam Bulbul v3
Provider: Sarvam AI | Hosting: Sarvam AI | Languages: 11 Indian languagesPurpose-built for Indian languages with 30+ speaker voices.
Best for: India-focused voice apps, regional language support.
Speech-to-Text
Deepgram Nova 3
Deepgram Nova 3
Provider: Deepgram | Hosting: SLNG + Deepgram | Languages: English, Spanish, HindiAvailable both SLNG-hosted and proxied.
Best for: low-latency streaming, voice agents.
Deepgram Nova 2
Deepgram Nova 2
Provider: Deepgram | Hosting: Deepgram | Languages: 36Proven model with VAD, diarization, and smart formatting.
Best for: production transcription, multi-speaker audio.
Soniox Speech AI v4
Soniox Speech AI v4
Provider: Soniox | Hosting: Soniox | Languages: 60+Real-time STT with speaker diarization, automatic language identification, and configurable endpoint detection. Returns native Soniox token frames.
Best for: multilingual streaming, multi-speaker conversations.
Reson8 STT v1
Reson8 STT v1
Provider: Reson8 | Hosting: Reson8 | Languages: 9 EuropeanReal-time STT with word-level timestamps, confidence scores, and partial results. Dutch, English, French, German, Italian, Polish, Portuguese, Spanish, Swedish.
Best for: European-language voice agents, low-latency transcription.
Sarvam Saaras v3
Sarvam Saaras v3
Provider: Sarvam AI | Hosting: Sarvam AI | Languages: 24Speech recognition for 24 Indian and European languages with code-mixing support. HTTP-only; not available over WebSocket.
Best for: India-focused batch transcription, code-switched audio.
Choosing a model
For voices, regions, and detailed model specs, see the Model Catalog.