explainx.ai350K+ learn from us
TrendingAI News TodayExplainx for Business
Pricing
explainx.ai

Upskill in AI — 16 free pathways, live workshops & bootcamps, and 50+ courses from practitioners. Plus the skills, tools, and MCP servers to practice on.

follow us

follow on google

Add explainx.ai as a preferred source

corporate training

support@explainx.ai

get started

Find your pathTake Free Evaluation

community

Join the community

learn

mind: share how you thinkpathways — start freeworkshopsbootcampscoursescompare Explainxcertificationsmock testsexplainx universitycorporate traininglearn skills & mcp

discover

skillsmcp serversexplainx mcpestacktoolsmdx readeragentsllmsdesignsdictionarypeopleagi trackerfelony benchranks

company

aboutvisionmissionteaminstructorsteach on explainxpartnershipscommunityhackathonscareers

content

daily AI newsstate of AI — live resultsblogreleasespromptsgeneratorsresource libraryfor LLMsexplainx.ai kids

solutions

all solutionsdeveloper upskillingmarketing upskillingproduct manager upskillingleadership upskilling

newsletter · weekly

Get AI news, tools, and insights in your inbox.

supportcontactprivacytermsdata rightshow we create contentsubmission guidelines

© 2026 AISOLO Technologies Pvt Ltd

explainx.ai

On this page

  • TL;DR: what shipped and what it costs
  • What Together announced
  • Voices, languages, and instructions
  • Pricing in context on Together
  • How to call the API
  • When to pick Together Qwen3 versus local or other APIs
  • Streaming HTTP versus WebSocket for voice agents
  • Cost math for product owners
  • What people are asking after the launch
  • Limits and honest caveats
  • Compliance and data handling checklist
  • Background: why Qwen3-TTS mattered before Together hosted it
  • Related reading
← Back to blog

explainx / blog

Qwen3 TTS on Together AI: Instruction Voices, 10 Languages, $20 per 1M Chars

Together AI, Qwen3 TTS, Text to Speech, Open Models, Developer Tools

Part of AI Tools and Apps

Together AI added Qwen3 TTS on Nov 20, 2026 with nine preset voices, plain-language delivery instructions, ten languages, and pricing at $20 per 1M characters.

Nov 20, 2026·8 min read·Yash Thakker
add explainx.ai
go deep
Qwen3 TTS on Together AI: Instruction Voices, 10 Languages, $20 per 1M Chars

Together AI added hosted Qwen3 TTS on November 20, 2026, with nine preset voices, plain-language delivery instructions, ten languages per voice, and pricing at $20 per 1 million characters. The company says its inference team tuned serving so first audio can start in as little as 97ms, aiming at live assistants rather than batch narration alone.

The launch sits next to Together Storage Accelerator and agent eval work as Together pitches the full stack, not only raw GPUs. For builders comparing open TTS, see Nari Labs' Qwen3-TTS serving write-up, Hugging Face speech-to-speech defaults, and Zyphra's ZONOS3-Mini release.

Daily briefFrom Yash · 350K+ students taught

Catch up on AI

One AI story explained in plain English, plus one thing to try. Every day, free. Unsubscribe anytime.

TL;DR: what shipped and what it costs

table · 2 cols
QuestionAnswer
Model idQwen/Qwen3-TTS-12Hz-1.7B per Together TTS docs
Price (Together list)$20 / 1M characters
VoicesNine presets (vivian, serena, ryan, aiden, …)
Languages10 (zh, en, ja, ko, de, fr, ru, pt, es, it)
Style controlextra_params.instructions (plain language, up to 500 chars)
Latency claimAs low as 97ms to first audio (Together launch post)
TimestampsWord alignment not supported on this model

What Together announced

In its November 20 launch post, Together frames Qwen3 TTS as separating who speaks from how they speak. You pick one of nine preset voices. The voice stays fixed while you change delivery with a short instruction such as excited and upbeat, or move the same voice across languages.

Together says the model is available on serverless inference and dedicated endpoints. The post highlights three demo angles: one English line read with three different instructions, one voice reading an order update in four languages, and latency tuned for real-time conversation.

Authors credited on the post include Anthony Ji, Charles Duong, Sebastien Beurnier, Sahil Yadav, and Sonny Khan. Pricing and API fields below come from Together's documentation, which Together updated to list Qwen3 alongside Orpheus and Kokoro.

Speech waveform lines illustrating Qwen3 TTS multilingual output on Together AISpeech waveform lines illustrating Qwen3 TTS multilingual output on Together AI

Voices, languages, and instructions

Together documents nine preset voices. Each has a native language but can speak every supported locale when you set language:

table · 2 cols
VoiceNative language (per Together docs)
vivian, serena, uncle_fu, dylan, ericChinese variants
ryan, aidenEnglish
ono_annaJapanese
soheeKorean

Supported language codes include zh, en, ja, ko, de, fr, ru, pt, es, it. That matters for products that want one branded voice across European and Asian locales without training a new speaker embedding per market.

Style instructions ride in extra_params.instructions. Together's docs show a congratulatory line with Speak warmly and happily. The same mechanism works with stream: true and on the WebSocket API when you set extra_params.instructions in tts_session.updated or on the connection URL.

Qwen3 TTS also supports an optional seed in extra_params for best-effort reproducibility when input, voice, and seed match.

Pricing in context on Together

Together's public price table in its TTS docs (fetched November 20, 2026) lists:

table · 2 cols
Model on TogetherPrice per 1M characters
Kokoro$4
Orpheus 3B$15
Qwen3 TTS 1.7B$20

That positions Qwen3 as a mid-tier hosted option: cheaper than Cartesia Sonic 2 at $65 on the same table, more than Kokoro, with instruction steering and multilingual presets as the differentiator.

Teams already optimizing Qwen3-TTS on owned hardware should still read Nari Labs' speed-cost frontier post, which reported sub-50ms p95 time-to-first-audio on one H100 with a custom stack. Together's 97ms figure is a hosted claim on Together's stack, not a universal ceiling for the model weights.

How to call the API

Together documents three delivery modes: standard HTTP, streaming HTTP for low time-to-first-byte, and WebSockets for interactive agents. Qwen3 supports wav, mp3, raw, and mulaw response formats. Sample rates are 24000 Hz default or 8000 Hz.

Example curl from Together docs (API key via environment):

bash
curl -X POST "https://api.together.ai/v1/audio/speech" \
  -H "Authorization: Bearer $TOGETHER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Qwen/Qwen3-TTS-12Hz-1.7B",
    "input": "Congratulations on the new job! I am really proud of you.",
    "voice": "ryan",
    "language": "en",
    "response_format": "wav",
    "extra_params": {"instructions": "Speak warmly and happily."}
  }' \
  --output speech.wav

For voice agents, Together points to a real-time STT plus TTS pipeline guide in the same docs set. Pair this endpoint with GPT Realtime voice APIs or local STT from superwhisper S1-mini depending on whether the LLM leg stays on Together or elsewhere.

API adapter diagram for hosted text-to-speech requests on Together AIAPI adapter diagram for hosted text-to-speech requests on Together AI

When to pick Together Qwen3 versus local or other APIs

Pick Together Qwen3 TTS when you want Qwen's instruction-steered presets without operating GPUs, you already bill inference to Together, or you need HTTP and WebSocket speech from one vendor next to Llama, Qwen LLMs, and GPU clusters.

Self-host or use another host when cost per million characters dominates at your volume, you need word timestamps, or you must keep audio on-prem for compliance. Voicebox-style local studios and Miso One remain relevant for teams optimizing capex over opex.

Compare hosted rivals using HeyGen on OpenRouter pricing claims and DeepL Voice Aure tone control when emotional range and translation matter more than open weights.

Streaming HTTP versus WebSocket for voice agents

Together's TTS docs draw a bright line between transport choices:

table · 3 cols
ModeBest forQwen3 notes
Standard HTTPBatch files, voicemail renders, offline clipsReturns complete wav or mp3
Streaming HTTPLow time-to-first-byte on full sentencesSupports stream: true with instructions
WebSocket APIChatbots that receive tokens incrementallySend partial text; audio chunks flow out

For a voice agent shaped like Hugging Face's speech-to-speech recipe, you might keep STT and the LLM on one stack and add Qwen3 on Together only for the TTS leg. That avoids shipping another GPU image just to test Alibaba's open weights.

If you already run Parakeet TDT plus a hosted LLM, swapping the TTS endpoint to Together is mostly a model string change plus voice name. Test language codes on every locale you ship; Together documents lowercase locale tags such as zh-hk for Cantonese variants on other models, while Qwen3 lists ten core languages.

Cost math for product owners

At $20 per million characters, rough napkin math:

table · 3 cols
Monthly spoken outputCharacter ballparkTogether Qwen3 bill (list price)
Light assistant500k chars~$10
Consumer app with daily briefings5M chars~$100
Call-center narration prototype50M chars~$1,000

Compare against GPU rental if you self-host Qwen3-TTS 1.7B: you pay electricity, ops, and engineering instead of the per-character meter. Nari Labs claimed about $2 per million characters at 10 RPS on one H100, but that assumed their custom stack, not your team's iteration time.

Kokoro on Together at $4 remains the budget tier when you only need intelligibility, not instruction steering across ten languages.

What people are asking after the launch

Do I need a dedicated endpoint? Together says serverless works day one; dedicated endpoints matter when you have steady QPS and want isolation. The launch post mentions both.

Can I clone a custom voice? Qwen3 on Together is preset voices only in the docs we read. Custom cloning paths live in other models (Orpheus voice names, Kokoro mixing) on the same platform.

Is this the same as Qwen3-TTS on Hugging Face? The weights family matches Qwen3-TTS-12Hz-1.7B, but Together adds its serving tuning and billing wrapper. Benchmark their TTFA in your region rather than trusting a single blog number.

Will instructions work in every language? Together demos show aiden reading English with emotional instructions, then the same voice in other languages. You still pass language explicitly; instructions are not a substitute for locale tags.

Limits and honest caveats

Together's docs are explicit about Qwen3 gaps:

  • No word-level alignment on this model.
  • No opus, aac, or flac output formats (unlike some Minimax models on the same platform).
  • Seed reproducibility is best-effort only.

The 97ms latency line is marketing copy on Together's blog until you benchmark your region, sentence length, and concurrent streams. For production voice agents, budget LLM time-to-first-token separately; as Hacker News commenters noted on Nari's post, TTS TTFA alone does not cap end-to-end conversational delay.

Compliance and data handling checklist

Together hosts customer text on inference. For regulated apps:

  • Log retention policies in your DPIA even when Together does not train on API traffic by default contract wording you sign.
  • Separate PII from prompts where possible; instructions fields are as sensitive as the spoken line.
  • Document voice choice in accessibility reviews; emotional instructions can skew perceived tone in banking or healthcare bots.

None of that is unique to Qwen3, but instruction-steered TTS makes marketing copy generation tempting — legal teams may want review gates before auto-speaking dynamic CRM fields.

Background: why Qwen3-TTS mattered before Together hosted it

Alibaba's Qwen team open-sourced Qwen3-TTS weights earlier in 2026, and explainx.ai already tracked serving optimizations (Nari Labs), local CPU stacks (Kokoro guide), and multi-model studios (Voicebox). Together's launch is the managed API layer: same family, vendor SLO, and a single invoice next to Llama or DeepSeek calls.

That matters for teams who standardized on Together during agent eval pushes or prefix-cache experiments and do not want a second GPU vendor only for speech.

Deep dive on instructions: treat them like a secondary prompt. Short, testable phrases beat paragraphs. Start with three templates (neutral, urgent, empathetic) per product surface and A/B listener studies before letting users type free-form instructions in production.

Related reading

  • Together Storage Accelerator
  • Together agent evals at 97% completion
  • Nari Labs Qwen3-TTS GPU serving
  • Hugging Face speech-to-speech pipeline
  • Kokoro local CPU TTS guide
  • OpenAI GPT Realtime voice models
  • Zyphra ZONOS3-Mini open TTS

Official sources: Together AI — Qwen3 TTS launch · Together AI — Text-to-speech documentation

Pricing, model ids, and latency claims are accurate as of November 20, 2026, per Together's blog and docs.

Spotted something out of date? Let us know.
Daily briefFrom Yash · 350K+ students taught

Catch up on AI

One AI story explained in plain English, plus one thing to try. Every day, free. Unsubscribe anytime.

  • ✓ Free
  • ✓ One email a day, no spam
  • ✓ Unsubscribe anytime
Yash Thakker

Written by

Yash Thakker

Yash is an AI expert with over 300K learners. Join his workshops →

View Yash Thakker in People in AI →

Related posts

Nov 19, 2026

Together Storage Accelerator: Free GPU-Cluster Caching With a 20x Warm-Read Claim

Together AI says its new Storage Accelerator cuts repeated data reads for GPU clusters by about 20x, fetches each object from the origin once per cluster, and costs nothing extra. Here is how it works, the measurements Together published, and what they do not show.

Nov 16, 2026

Hugging Face Routes Hub Inference Through OpenRouter: One Token, Many Providers

Hugging Face and OpenRouter announced on November 16, 2026 that language-model inference on the Hub now routes through OpenRouter instead of a custom router. Builders keep one Hugging Face token while OpenRouter picks among 80+ providers by price, speed, and reliability.

Nov 10, 2026

Apple Harbor App: Mac Local AI Inference Cluster — Claimed vs Verified

On November 10, 2026, leak accounts published Harbor marketing text: a Claris private preview app that clusters Apple silicon Macs over Thunderbolt 5 for local open-weight models. Apple's WWDC26 MLX server video confirms the stack underneath. This post separates leak copy from official docs and lists what builders can run today.