Text-to-speech (TTS)

Model details on this page come from each provider’s official documentation and announcements, checked on October 16, 2026. Providers update models, benchmarks, language support and availability often. Always check the linked official source for the latest information before choosing a model.

Text-to-speech models turn the agent’s reply into spoken audio. Select one in the TTS Model field of the Voice Agent configuration.

At a glance

Model	Provider	Model ID	Highlights	Official docs
Flash v2.5	ElevenLabs	`eleven_flash_v2_5`	ElevenLabs’ fastest model, ~75 ms	ElevenLabs
Turbo v2.5	ElevenLabs	`eleven_turbo_v2_5`	Low latency (deprecated by ElevenLabs)	ElevenLabs
v3 Conversational	ElevenLabs	`eleven_v3_conversational`	Expressive real-time speech with audio tags	ElevenLabs
v4 Turbo	ElevenLabs	`eleven_v4_turbo`	ElevenLabs’ most emotive real-time model, ~100 ms	ElevenLabs
Sonic 3	Cartesia	`sonic-3`	Previous-generation Sonic model	Cartesia
Sonic 3.5	Cartesia	`sonic-3.5`	Sub-90 ms, accurate alphanumerics	Cartesia
Gemini 3.8 Flash Lite TTS	Google	`gemini-3.8-flash-lite-tts`	Fast, cost-efficient Gemini TTS	Google
Gemini 3.1 Flash TTS	Google	`gemini-3.1-flash-tts-preview`	Steerable prompts and audio tags (legacy preview)	Google
Gemini 2.5 Flash TTS	Google	`gemini-2.5-flash-tts`	Controllable single- and multi-speaker speech	Google Cloud
Default	Google	`default`	Google Cloud Text-to-Speech voices	Google Cloud
GPT 4o mini TTS	OpenAI	`gpt-4o-mini-tts`	Steer tone and style with instructions	OpenAI
Default	Azure	`default`	Azure neural voices, under 300 ms	Microsoft
TTS 1.5 max	Inworld	`inworld-tts-1.5-max`	Balanced quality and speed (deprecated by Inworld)	Inworld
TTS 1.5 mini	Inworld	`inworld-tts-1.5-mini`	Lowest latency (deprecated by Inworld)	Inworld
Falcon 2	Murf	`falcon-2`	Under 100 ms time to first audio	Murf
Bulbul v3	Sarvam	`bulbul:v3`	Indian languages, strong on 8 kHz telephony	Sarvam

ElevenLabs

Flash v2.5

eleven_flash_v2_5 · Official docs “Our fast, affordable speech synthesis model”. ElevenLabs says it is its fastest model, built for real-time use and the ElevenLabs Agents Platform.

Metric	Value	Source
Latency	~75 ms, excluding application and network latency	ElevenLabs
Languages (provider)	32	ElevenLabs
Character limit per request	40,000 (~40 minutes of audio)	ElevenLabs

Languages available in SubVerse AI (42)

Arabic (Kuwait) (ar-KW)
Arabic (Saudi Arabia) (ar-SA)
Arabic (UAE) (ar-AE)
Bulgarian (bg-BG)
Chinese, Mandarin (Traditional, Taiwan) (cmn-Hant-TW)
Croatian (hr-HR)
Czech (cs-CZ)
Danish (da-DK)
Dutch (nl-NL)
English (Australia) (en-AU)
English (Canada) (en-CA)
English (India) (en-IN)
English (UK) (en-GB)
English (US) (en-US)
Filipino (fil-PH)
Finnish (fi-FI)
French (Canada) (fr-CA)
French (France) (fr-FR)
German (de-DE)
Greek (el-GR)
Hindi (hi-IN)
Hungarian (hu-HU)
Indonesian (id-ID)
Italian (it-IT)
Japanese (ja-JP)
Korean (ko-KR)
Malay (ms-MY)
Norwegian (no-NO)
Polish (pl-PL)
Portuguese (Brazil) (pt-BR)
Portuguese (Portugal) (pt-PT)
Romanian (ro-RO)
Russian (ru-RU)
Slovak (sk-SK)
Spanish (Mexico) (es-MX)
Spanish (Spain) (es-ES)
Spanish (US) (es-US)
Swedish (sv-SE)
Tamil (ta-IN)
Turkish (tr-TR)
Ukrainian (uk-UA)
Vietnamese (vi-VN)

Turbo v2.5

eleven_turbo_v2_5 · Official docs

ElevenLabs lists Turbo v2.5 under Deprecated models as a “first generation low-latency model (outclassed by Flash models)”. It says Turbo v2.5 is functionally equivalent to Flash v2.5, Flash has lower latency on average, and it recommends Flash models “in all use cases”.

Metric	Value	Source
Languages (provider)	32	ElevenLabs

Languages available in SubVerse AI (42)

Arabic (Kuwait) (ar-KW)
Arabic (Saudi Arabia) (ar-SA)
Arabic (UAE) (ar-AE)
Bulgarian (bg-BG)
Chinese, Mandarin (Traditional, Taiwan) (cmn-Hant-TW)
Croatian (hr-HR)
Czech (cs-CZ)
Danish (da-DK)
Dutch (nl-NL)
English (Australia) (en-AU)
English (Canada) (en-CA)
English (India) (en-IN)
English (UK) (en-GB)
English (US) (en-US)
Filipino (fil-PH)
Finnish (fi-FI)
French (Canada) (fr-CA)
French (France) (fr-FR)
German (de-DE)
Greek (el-GR)
Hindi (hi-IN)
Hungarian (hu-HU)
Indonesian (id-ID)
Italian (it-IT)
Japanese (ja-JP)
Korean (ko-KR)
Malay (ms-MY)
Norwegian (no-NO)
Polish (pl-PL)
Portuguese (Brazil) (pt-BR)
Portuguese (Portugal) (pt-PT)
Romanian (ro-RO)
Russian (ru-RU)
Slovak (sk-SK)
Spanish (Mexico) (es-MX)
Spanish (Spain) (es-ES)
Spanish (US) (es-US)
Swedish (sv-SE)
Tamil (ta-IN)
Turkish (tr-TR)
Ukrainian (uk-UA)
Vietnamese (vi-VN)

v3 Conversational

eleven_v3_conversational · Official docs “Our expressive, realtime speech synthesis model”, the real-time version of Eleven v3. It supports audio tags for fine-grained control of delivery. ElevenLabs now describes it as its previous generation real-time model.

Metric	Value	Source
Latency	~280 ms, excluding application and network latency	ElevenLabs
Languages (provider)	70+	ElevenLabs
Expressiveness	Audio tags such as `[excited]`, `[whispers]` and `[sighs]`	ElevenLabs

Languages available in SubVerse AI (53)

Arabic (Kuwait) (ar-KW)
Arabic (Saudi Arabia) (ar-SA)
Arabic (UAE) (ar-AE)
Assamese (as-IN)
Bengali (bn-IN)
Bulgarian (bg-BG)
Chinese, Mandarin (Traditional, Taiwan) (cmn-Hant-TW)
Croatian (hr-HR)
Czech (cs-CZ)
Danish (da-DK)
Dutch (nl-NL)
English (Australia) (en-AU)
English (Canada) (en-CA)
English (India) (en-IN)
English (UK) (en-GB)
English (US) (en-US)
Filipino (fil-PH)
Finnish (fi-FI)
French (Canada) (fr-CA)
French (France) (fr-FR)
Georgian (ka-GE)
German (de-DE)
Greek (el-GR)
Gujarati (gu-IN)
Hebrew (he-IL)
Hindi (hi-IN)
Hungarian (hu-HU)
Indonesian (id-ID)
Italian (it-IT)
Japanese (ja-JP)
Kannada (kn-IN)
Korean (ko-KR)
Malay (ms-MY)
Malayalam (ml-IN)
Marathi (mr-IN)
Norwegian (no-NO)
Polish (pl-PL)
Portuguese (Brazil) (pt-BR)
Portuguese (Portugal) (pt-PT)
Punjabi (pa-IN)
Romanian (ro-RO)
Russian (ru-RU)
Slovak (sk-SK)
Spanish (Mexico) (es-MX)
Spanish (Spain) (es-ES)
Spanish (US) (es-US)
Swedish (sv-SE)
Tamil (ta-IN)
Telugu (te-IN)
Thai (th-TH)
Turkish (tr-TR)
Ukrainian (uk-UA)
Vietnamese (vi-VN)

v4 Turbo

eleven_v4_turbo · Official docs “Our most emotive, real-time speech synthesis model”. ElevenLabs recommends it for low-latency use and for “the most expressive delivery” on its Agents Platform, for example support agents, AI assistants and interactive characters.

Metric	Value	Source
Median inference latency	~100 ms, excluding application and network latency	ElevenLabs
Languages (provider)	90+, including Hindi, Bengali, Tamil, Telugu, Gujarati, Kannada, Malayalam, Marathi, Odia, Punjabi and Urdu	ElevenLabs
Features	Audio tags, voice cloning	ElevenLabs

Languages available in SubVerse AI (53)

Arabic (Kuwait) (ar-KW)
Arabic (Saudi Arabia) (ar-SA)
Arabic (UAE) (ar-AE)
Assamese (as-IN)
Bengali (bn-IN)
Bulgarian (bg-BG)
Chinese, Mandarin (Traditional, Taiwan) (cmn-Hant-TW)
Croatian (hr-HR)
Czech (cs-CZ)
Danish (da-DK)
Dutch (nl-NL)
English (Australia) (en-AU)
English (Canada) (en-CA)
English (India) (en-IN)
English (UK) (en-GB)
English (US) (en-US)
Filipino (fil-PH)
Finnish (fi-FI)
French (Canada) (fr-CA)
French (France) (fr-FR)
Georgian (ka-GE)
German (de-DE)
Greek (el-GR)
Gujarati (gu-IN)
Hebrew (he-IL)
Hindi (hi-IN)
Hungarian (hu-HU)
Indonesian (id-ID)
Italian (it-IT)
Japanese (ja-JP)
Kannada (kn-IN)
Korean (ko-KR)
Malay (ms-MY)
Malayalam (ml-IN)
Marathi (mr-IN)
Norwegian (no-NO)
Polish (pl-PL)
Portuguese (Brazil) (pt-BR)
Portuguese (Portugal) (pt-PT)
Punjabi (pa-IN)
Romanian (ro-RO)
Russian (ru-RU)
Slovak (sk-SK)
Spanish (Mexico) (es-MX)
Spanish (Spain) (es-ES)
Spanish (US) (es-US)
Swedish (sv-SE)
Tamil (ta-IN)
Telugu (te-IN)
Thai (th-TH)
Turkish (tr-TR)
Ukrainian (uk-UA)
Vietnamese (vi-VN)

Cartesia

Sonic 3

sonic-3 · Official docs Cartesia now lists Sonic 3 under Older Models, which it continues to serve for compatibility. Cartesia describes Sonic 3.5 as “a drop-in replacement for Sonic 3 for most customers”.

Metric	Value	Source
Speech Arena quality · Third-party	1058 Elo (±12)	Artificial Analysis
Speed and volume controls	Speed 0.6–1.5, volume 0.5–2.0 (beta)	Cartesia

Cartesia no longer publishes performance figures for Sonic 3. The Third-party figure is published by Artificial Analysis, an independent benchmarking company, not by Cartesia. It comes from blind listener preference votes. Accessed October 16, 2026.

Languages available in SubVerse AI (49)

Arabic (Kuwait) (ar-KW)
Arabic (Saudi Arabia) (ar-SA)
Arabic (UAE) (ar-AE)
Bengali (bn-IN)
Bulgarian (bg-BG)
Chinese, Mandarin (Traditional, Taiwan) (cmn-Hant-TW)
Croatian (hr-HR)
Czech (cs-CZ)
Danish (da-DK)
Dutch (nl-NL)
English (Australia) (en-AU)
English (Canada) (en-CA)
English (India) (en-IN)
English (UK) (en-GB)
English (US) (en-US)
Filipino (fil-PH)
Finnish (fi-FI)
French (Canada) (fr-CA)
French (France) (fr-FR)
German (de-DE)
Greek (el-GR)
Gujarati (gu-IN)
Hindi (hi-IN)
Hungarian (hu-HU)
Indonesian (id-ID)
Italian (it-IT)
Japanese (ja-JP)
Kannada (kn-IN)
Korean (ko-KR)
Malay (ms-MY)
Malayalam (ml-IN)
Marathi (mr-IN)
Norwegian (no-NO)
Polish (pl-PL)
Portuguese (Brazil) (pt-BR)
Portuguese (Portugal) (pt-PT)
Punjabi (pa-IN)
Romanian (ro-RO)
Russian (ru-RU)
Slovak (sk-SK)
Spanish (Mexico) (es-MX)
Spanish (Spain) (es-ES)
Spanish (US) (es-US)
Swedish (sv-SE)
Tamil (ta-IN)
Telugu (te-IN)
Turkish (tr-TR)
Ukrainian (uk-UA)
Vietnamese (vi-VN)

Sonic 3.5

sonic-3.5 · Official docs Cartesia says Sonic 3.5 “follows your transcript faithfully, voices confirmation codes and heteronyms correctly without preprocessing”. Compared with Sonic 3, Cartesia highlights more natural pacing and emotion, cleaner audio, better alphanumeric read-out and stronger multilingual performance.

Metric	Value	Source
Latency	Sub-90 ms	Cartesia
Languages (provider)	42	Cartesia
Speed and volume controls	Speed 0.6–1.5, volume 0.5–2.0 (beta)	Cartesia

Languages available in SubVerse AI (52)

Arabic (Kuwait) (ar-KW)
Arabic (Saudi Arabia) (ar-SA)
Arabic (UAE) (ar-AE)
Bengali (bn-IN)
Bulgarian (bg-BG)
Chinese, Mandarin (Traditional, Taiwan) (cmn-Hant-TW)
Croatian (hr-HR)
Czech (cs-CZ)
Danish (da-DK)
Dutch (nl-NL)
English (Australia) (en-AU)
English (Canada) (en-CA)
English (India) (en-IN)
English (UK) (en-GB)
English (US) (en-US)
Filipino (fil-PH)
Finnish (fi-FI)
French (Canada) (fr-CA)
French (France) (fr-FR)
Georgian (ka-GE)
German (de-DE)
Greek (el-GR)
Gujarati (gu-IN)
Hebrew (he-IL)
Hindi (hi-IN)
Hungarian (hu-HU)
Indonesian (id-ID)
Italian (it-IT)
Japanese (ja-JP)
Kannada (kn-IN)
Korean (ko-KR)
Malay (ms-MY)
Malayalam (ml-IN)
Marathi (mr-IN)
Norwegian (no-NO)
Polish (pl-PL)
Portuguese (Brazil) (pt-BR)
Portuguese (Portugal) (pt-PT)
Punjabi (pa-IN)
Romanian (ro-RO)
Russian (ru-RU)
Slovak (sk-SK)
Spanish (Mexico) (es-MX)
Spanish (Spain) (es-ES)
Spanish (US) (es-US)
Swedish (sv-SE)
Tamil (ta-IN)
Telugu (te-IN)
Thai (th-TH)
Turkish (tr-TR)
Ukrainian (uk-UA)
Vietnamese (vi-VN)

Google

Gemini 3.8 Flash Lite TTS

gemini-3.8-flash-lite-tts · Official docs Google’s “fast, cost-efficient workhorse text-to-speech model”, built to replace Gemini 3.1 Flash TTS for high-volume production, voice agents and read-aloud features. Generally available since September 22, 2026.

Metric	Value	Source
Languages (provider)	101	Google
Voices	30 prebuilt voices	Google
Expressiveness	Style instructions and inline tags such as `<laugh>`, `<sigh>` and `<short pause>`	Google
Speech Arena quality · Third-party	1248 Elo (±14)	Artificial Analysis

Google does not publish quality or latency figures for this model on its model page. The Third-party figure is published by Artificial Analysis, an independent benchmarking company, not by Google. It comes from blind listener preference votes. Accessed October 16, 2026.

Languages available in SubVerse AI (22)

Dutch (nl-NL)
English (India) (en-IN)
English (US) (en-US)
French (France) (fr-FR)
German (de-DE)
Gujarati (gu-IN)
Hindi (hi-IN)
Indonesian (id-ID)
Italian (it-IT)
Japanese (ja-JP)
Korean (ko-KR)
Marathi (mr-IN)
Polish (pl-PL)
Portuguese (Brazil) (pt-BR)
Romanian (ro-RO)
Russian (ru-RU)
Spanish (Spain) (es-ES)
Tamil (ta-IN)
Telugu (te-IN)
Turkish (tr-TR)
Ukrainian (uk-UA)
Vietnamese (vi-VN)

Gemini 3.1 Flash TTS

gemini-3.1-flash-tts-preview · Official docs “Low-latency speech generation with natural outputs, steerable prompts, and expressive audio tags.”

Google lists this model as a legacy preview, with a shutdown date of November 17, 2026 on the Gemini API. Google recommends migrating to Gemini 3.8 Flash TTS or Gemini 3.8 Flash Lite TTS. See Gemini deprecations.

Metric	Value	Source
Speech Arena quality, as reported by Google	1,211 Elo on the Artificial Analysis TTS leaderboard	Google
Languages (provider)	70+	Google

Languages available in SubVerse AI (22)

Dutch (nl-NL)
English (India) (en-IN)
English (US) (en-US)
French (France) (fr-FR)
German (de-DE)
Gujarati (gu-IN)
Hindi (hi-IN)
Indonesian (id-ID)
Italian (it-IT)
Japanese (ja-JP)
Korean (ko-KR)
Marathi (mr-IN)
Polish (pl-PL)
Portuguese (Brazil) (pt-BR)
Romanian (ro-RO)
Russian (ru-RU)
Spanish (Spain) (es-ES)
Tamil (ta-IN)
Telugu (te-IN)
Turkish (tr-TR)
Ukrainian (uk-UA)
Vietnamese (vi-VN)

Gemini 2.5 Flash TTS

gemini-2.5-flash-tts · Official docs Optimized for low-latency, controllable, single- and multi-speaker speech generation for “cost-efficient everyday applications”.

Metric	Value	Source
Voices	30	Google Cloud
Speech Arena quality · Third-party	1059 Elo (±12)	Artificial Analysis

Google does not publish quality or latency figures for this model. The Third-party figure is published by Artificial Analysis, an independent benchmarking company, not by Google. It comes from blind listener preference votes. Accessed October 16, 2026.

Languages available in SubVerse AI (22)

Dutch (nl-NL)
English (India) (en-IN)
English (US) (en-US)
French (France) (fr-FR)
German (de-DE)
Gujarati (gu-IN)
Hindi (hi-IN)
Indonesian (id-ID)
Italian (it-IT)
Japanese (ja-JP)
Korean (ko-KR)
Marathi (mr-IN)
Polish (pl-PL)
Portuguese (Brazil) (pt-BR)
Romanian (ro-RO)
Russian (ru-RU)
Spanish (Spain) (es-ES)
Tamil (ta-IN)
Telugu (te-IN)
Turkish (tr-TR)
Ukrainian (uk-UA)
Vietnamese (vi-VN)

Default (Google)

default · Official docs The Google Default option uses Google Cloud Text-to-Speech voices. Google offers several voice types, and quality and features depend on the voice you choose:

Voice type	Google’s description
Chirp 3: HD	Intended for conversational agents. Supports low-latency real-time streaming.
Studio	Narration, news reading and broadcast
Neural2	General purpose
WaveNet	General purpose, premium voices trained on raw human speech
Standard	Cost-efficient

Source: Google Cloud. Google does not publish quality or latency figures for these voice types.

Languages available in SubVerse AI (42)

Arabic (Kuwait) (ar-KW)
Arabic (Saudi Arabia) (ar-SA)
Arabic (UAE) (ar-AE)
Bengali (bn-IN)
Bulgarian (bg-BG)
Croatian (hr-HR)
Czech (cs-CZ)
Danish (da-DK)
Dutch (nl-NL)
English (Australia) (en-AU)
English (India) (en-IN)
English (UK) (en-GB)
English (US) (en-US)
Finnish (fi-FI)
French (Canada) (fr-CA)
French (France) (fr-FR)
German (de-DE)
Greek (el-GR)
Gujarati (gu-IN)
Hindi (hi-IN)
Hungarian (hu-HU)
Indonesian (id-ID)
Italian (it-IT)
Japanese (ja-JP)
Kannada (kn-IN)
Korean (ko-KR)
Malayalam (ml-IN)
Marathi (mr-IN)
Polish (pl-PL)
Portuguese (Brazil) (pt-BR)
Punjabi (pa-IN)
Romanian (ro-RO)
Russian (ru-RU)
Slovak (sk-SK)
Spanish (Spain) (es-ES)
Spanish (US) (es-US)
Swedish (sv-SE)
Tamil (ta-IN)
Telugu (te-IN)
Turkish (tr-TR)
Ukrainian (uk-UA)
Vietnamese (vi-VN)

OpenAI

GPT 4o mini TTS

gpt-4o-mini-tts · Official docs A text-to-speech model built on GPT-4o mini. You can prompt it to control accent, emotional range, intonation, impressions, speed of speech, tone and whispering.

Detail	Value	Source
Voices	13 built-in voices. OpenAI recommends `marin` or `cedar` for best quality. Voices are optimized for English.	OpenAI
Language support	Generally follows the Whisper model’s language support	OpenAI
Max input	2,000 tokens	OpenAI
Benchmarks	Not published. No independent figures found.	—

Languages available in SubVerse AI (44)

Arabic (Kuwait) (ar-KW)
Arabic (Saudi Arabia) (ar-SA)
Arabic (UAE) (ar-AE)
Bulgarian (bg-BG)
Chinese, Mandarin (Traditional, Taiwan) (cmn-Hant-TW)
Croatian (hr-HR)
Czech (cs-CZ)
Danish (da-DK)
Dutch (nl-NL)
English (Australia) (en-AU)
English (Canada) (en-CA)
English (India) (en-IN)
English (UK) (en-GB)
English (US) (en-US)
Filipino (fil-PH)
Finnish (fi-FI)
French (Canada) (fr-CA)
French (France) (fr-FR)
German (de-DE)
Greek (el-GR)
Hindi (hi-IN)
Hungarian (hu-HU)
Indonesian (id-ID)
Italian (it-IT)
Japanese (ja-JP)
Kannada (kn-IN)
Korean (ko-KR)
Malay (ms-MY)
Marathi (mr-IN)
Norwegian (no-NO)
Polish (pl-PL)
Portuguese (Brazil) (pt-BR)
Portuguese (Portugal) (pt-PT)
Romanian (ro-RO)
Russian (ru-RU)
Slovak (sk-SK)
Spanish (Mexico) (es-MX)
Spanish (Spain) (es-ES)
Spanish (US) (es-US)
Swedish (sv-SE)
Tamil (ta-IN)
Turkish (tr-TR)
Ukrainian (uk-UA)
Vietnamese (vi-VN)

Azure

Default (Azure)

default · Official docs The Azure Default option uses Azure AI Speech standard neural voices. Microsoft describes these as “high-quality neural voices available out of the box in 100+ languages and locales”.

Metric	Value	Source
Latency (standard, non-HD voices)	Less than 300 ms	Microsoft
Number of voices (standard)	More than 500	Microsoft
Controls	Pitch, pauses, speaking rate and volume via SSML	Microsoft

Languages available in SubVerse AI (50)

Arabic (Kuwait) (ar-KW)
Arabic (Saudi Arabia) (ar-SA)
Arabic (UAE) (ar-AE)
Bengali (bn-IN)
Bulgarian (bg-BG)
Chinese, Mandarin (Traditional, Taiwan) (cmn-Hant-TW)
Croatian (hr-HR)
Czech (cs-CZ)
Danish (da-DK)
Dutch (nl-NL)
English (Australia) (en-AU)
English (Canada) (en-CA)
English (India) (en-IN)
English (UK) (en-GB)
English (US) (en-US)
Filipino (fil-PH)
Finnish (fi-FI)
French (Canada) (fr-CA)
French (France) (fr-FR)
German (de-DE)
Greek (el-GR)
Gujarati (gu-IN)
Hindi (hi-IN)
Hungarian (hu-HU)
Indonesian (id-ID)
Italian (it-IT)
Japanese (ja-JP)
Kannada (kn-IN)
Korean (ko-KR)
Malay (ms-MY)
Malayalam (ml-IN)
Marathi (mr-IN)
Norwegian (no-NO)
Odia (od-IN)
Polish (pl-PL)
Portuguese (Brazil) (pt-BR)
Portuguese (Portugal) (pt-PT)
Punjabi (pa-IN)
Romanian (ro-RO)
Russian (ru-RU)
Slovak (sk-SK)
Spanish (Mexico) (es-MX)
Spanish (Spain) (es-ES)
Spanish (US) (es-US)
Swedish (sv-SE)
Tamil (ta-IN)
Telugu (te-IN)
Turkish (tr-TR)
Ukrainian (uk-UA)
Vietnamese (vi-VN)

Inworld

Inworld lists TTS 1.5 max and TTS 1.5 mini as deprecated and not recommended for new projects, and recommends its TTS-2 models instead. See Inworld TTS models.

TTS 1.5 max

inworld-tts-1.5-max · Official docs Inworld describes TTS 1.5 max as its flagship model at launch, with the “best balance of quality and speed”.

Metric	Value	Source
Time to first audio (P90)	Under 250 ms	Inworld
Expressiveness	30% more expressive than prior generations	Inworld
Word error rate	40% lower than prior generations	Inworld
Languages (provider)	15	Inworld

Languages available in SubVerse AI (25)

Arabic (Kuwait) (ar-KW)
Arabic (Saudi Arabia) (ar-SA)
Arabic (UAE) (ar-AE)
Chinese, Mandarin (Traditional, Taiwan) (cmn-Hant-TW)
Dutch (nl-NL)
English (Australia) (en-AU)
English (Canada) (en-CA)
English (India) (en-IN)
English (UK) (en-GB)
English (US) (en-US)
French (Canada) (fr-CA)
French (France) (fr-FR)
German (de-DE)
Hebrew (he-IL)
Hindi (hi-IN)
Italian (it-IT)
Japanese (ja-JP)
Korean (ko-KR)
Polish (pl-PL)
Portuguese (Brazil) (pt-BR)
Portuguese (Portugal) (pt-PT)
Russian (ru-RU)
Spanish (Mexico) (es-MX)
Spanish (Spain) (es-ES)
Spanish (US) (es-US)

TTS 1.5 mini

inworld-tts-1.5-mini · Official docs Inworld describes TTS 1.5 mini as “optimized for hyper-latency sensitive applications”.

Metric	Value	Source
Time to first audio (P90)	Under 130 ms	Inworld
Languages (provider)	15	Inworld

Languages available in SubVerse AI (25)

Arabic (Kuwait) (ar-KW)
Arabic (Saudi Arabia) (ar-SA)
Arabic (UAE) (ar-AE)
Chinese, Mandarin (Traditional, Taiwan) (cmn-Hant-TW)
Dutch (nl-NL)
English (Australia) (en-AU)
English (Canada) (en-CA)
English (India) (en-IN)
English (UK) (en-GB)
English (US) (en-US)
French (Canada) (fr-CA)
French (France) (fr-FR)
German (de-DE)
Hebrew (he-IL)
Hindi (hi-IN)
Italian (it-IT)
Japanese (ja-JP)
Korean (ko-KR)
Polish (pl-PL)
Portuguese (Brazil) (pt-BR)
Portuguese (Portugal) (pt-PT)
Russian (ru-RU)
Spanish (Mexico) (es-MX)
Spanish (Spain) (es-ES)
Spanish (US) (es-US)

Murf

Falcon 2

falcon-2 · Official docs “An ultra-fast, scalable, and reliable speech synthesis model built for real-time conversational AI.” It can switch languages within a single sentence.

Metric	Value	Source
Time to first audio	Under 100 ms	Murf
Median time to first audio, by region	61–97 ms (1,500+ streaming requests from 32 global locations)	Murf benchmarks
Pronunciation accuracy	99.37%	Murf
Concurrency	10,000+ concurrent calls	Murf
Voices	150+ voices in 20+ expressive styles	Murf

Languages available in SubVerse AI (34)

Assamese (as-IN)
Bengali (bn-IN)
Chinese, Mandarin (Simplified) (zh-CN)
Croatian (hr-HR)
Dutch (nl-NL)
English (Australia) (en-AU)
English (India) (en-IN)
English (Scotland) (en-SCOTT)
English (UK) (en-UK)
English (US) (en-US)
Filipino (Tagalog) (tl-PH)
French (Canada) (fr-CA)
French (France) (fr-FR)
German (de-DE)
Greek (el-GR)
Gujarati (gu-IN)
Hindi (hi-IN)
Hindi (Latin script) (hi-LATN)
Italian (it-IT)
Japanese (ja-JP)
Kannada (kn-IN)
Korean (ko-KR)
Malayalam (ml-IN)
Marathi (mr-IN)
Odia (or-IN)
Polish (pl-PL)
Portuguese (Brazil) (pt-BR)
Punjabi (pa-IN)
Slovak (sk-SK)
Spanish (Mexico) (es-MX)
Spanish (Spain) (es-ES)
Tamil (ta-IN)
Telugu (te-IN)
Turkish (tr-TR)

Sarvam

Bulbul v3

bulbul:v3 · Official docs Sarvam’s text-to-speech model for Indian languages, with 30+ voices from professional voice artists.

Metric	Value	Source
Listening study	Independent blind A/B test by Josh Talks: 11 languages, 20,000+ votes, compared with ElevenLabs v3 alpha, ElevenLabs Flash v2.5 and Cartesia Sonic 3	Sarvam
8 kHz telephony audio	”The clear top performer” in the study	Sarvam
Full-band audio	ElevenLabs v3 alpha led on audio quality; Bulbul v3 ranked ahead of the other models tested	Sarvam
Characters per request	2,500	Sarvam

Sarvam now lists bulbul:v4-flash as its latest model for new integrations. Bulbul v3 remains stable.

Languages available in SubVerse AI (11)

Bengali (bn-IN)
English (India) (en-IN)
Gujarati (gu-IN)
Hindi (hi-IN)
Kannada (kn-IN)
Malayalam (ml-IN)
Marathi (mr-IN)
Odia (od-IN)
Punjabi (pa-IN)
Tamil (ta-IN)
Telugu (te-IN)

Providers measure latency differently. Some exclude network time, some measure end to end, and some report medians while others report P90. Figures from different providers are not directly comparable. Test candidate voices with your own scripts and telephony setup.

Overview

Model Types

Reference

At a glance

ElevenLabs

Flash v2.5

Turbo v2.5

v3 Conversational

v4 Turbo

Cartesia

Sonic 3

Sonic 3.5

Google

Gemini 3.8 Flash Lite TTS

Gemini 3.1 Flash TTS

Gemini 2.5 Flash TTS

Default (Google)

OpenAI

GPT 4o mini TTS

Azure

Default (Azure)

Inworld

TTS 1.5 max

TTS 1.5 mini

Murf

Falcon 2

Sarvam

Bulbul v3

​At a glance

​ElevenLabs

​Flash v2.5

​Turbo v2.5

​v3 Conversational

​v4 Turbo

​Cartesia

​Sonic 3

​Sonic 3.5

​Google

​Gemini 3.8 Flash Lite TTS

​Gemini 3.1 Flash TTS

​Gemini 2.5 Flash TTS

​Default (Google)

​OpenAI

​GPT 4o mini TTS

​Azure

​Default (Azure)

​Inworld

​TTS 1.5 max

​TTS 1.5 mini

​Murf

​Falcon 2

​Sarvam

​Bulbul v3

At a glance

ElevenLabs

Flash v2.5

Turbo v2.5

v3 Conversational

v4 Turbo

Cartesia

Sonic 3

Sonic 3.5

Google

Gemini 3.8 Flash Lite TTS

Gemini 3.1 Flash TTS

Gemini 2.5 Flash TTS

Default (Google)

OpenAI

GPT 4o mini TTS

Azure

Default (Azure)

Inworld

TTS 1.5 max

TTS 1.5 mini

Murf

Falcon 2

Sarvam

Bulbul v3