Head to head · Text-to-speech · October 2026 research run
ElevenLabs Text to Speech API + MCP vs Soniox Text-to-Speech
ElevenLabs Text to Speech API + MCP scores 77.8 (BB) on agent readiness against Soniox Text-to-Speech's 71.8 (BB), and leads in 4 of 7 scored categories. Soniox Text-to-Speech leads on reliability, security & auth and transparency & trust. Both do text-to-speech.
Best text-to-speech APIs for AI agents · All 148 tts comparisons
Which one, for what
ElevenLabs Text to Speech API + MCP BB
Best for Best when an agent needs many languages, many voices or the most expressive models from one vendor, and the operator can accept training by default or pay for Enterprise.
Ahead on
- Schema & documentation, 94 against 85
- Agent ergonomics, 92 against 78
- Payments & pricing, 60 against 30
- Maintenance & community, 77 against 63
Also in its favour
- Runs on your own machine
- Rated higher by the reviewer agents, 3.5 against 3.0 out of 5
- No incidents deducted, where Soniox Text-to-Speech loses 3 points for them
Watch for
Content may be used for training unless you opt out under Data use, though the Eleven v4 launch page says it isn't used without consent
Best for Multilingual agents that need any voice in any of 60-plus languages, short turns and strict data handling.
Ahead on
- Reliability, 87 against 80
- Security & auth, 87 against 65
- Transparency & trust, 73 against 68
Watch for
Audio stops at 2 minutes per request or stream and the cap can't be raised
Why the edge
Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.
Payments & pricing ElevenLabs Text to Speech API + MCP +30
ElevenLabs Text to Speech API + MCP 60
No x402, MPP or L402 (0). Per-1,000-character prices for every model published without a login, re-read on 1 November, $0.08 on v4, v3 and Multilingual v2 and $0.04 on v4 Turbo, v3 Conversational and Flash (20). Free plan with 10,000 v4 characters a month and no card, per the 5 October check. The pricing page read on 1 November lists card, Apple Pay and Google Pay for paid subscriptions and doesn't say the free plan needs one (20). A person signs up in a browser (0). 0 + 20 + 20 + 0 = 40. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 40 is 60.
Soniox Text-to-Speech 30
No x402, MPP or L402 (0). Token prices published without a login, $4.00 per 1M input tokens and $21.50 per 1M output tokens, which Soniox puts at about $0.70 an hour, re-read on 2 November (20). No free credits for new accounts found (0). A person signs up and funds the account in a browser; the new organisation API needs an organisation key from that account (0). 0 + 20 + 0 + 0 = 20. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 20 is 30.
Security & auth Soniox Text-to-Speech +22
ElevenLabs Text to Speech API + MCP 65
Model reading of the checklist, with training and retention in place of least-privilege and injection lines. Keys can be restricted to chosen endpoints, given a credit quota and limited to IP addresses or CIDR ranges, the docs walk through rotation, service accounts hold keys that don't belong to a person, and user keys and (since 26 October) service account keys can be set to expire (30). The Terms (updated 9 October 2026, re-read on 1 November) still let ElevenLabs use content to improve its models, with an opt-out under Data use in account settings that only applies going forward (10). TTS text and audio are kept by default and zero retention through enable_logging=false is Enterprise only (5). The generation history lists each request, though we found no audit log of key actions (10 of 15). A valid security.txt (expiring 6 October 2027, re-read on 1 November) pointing to a report form, and the Eleven v4 launch page states SOC 2 Type II, ISO 27001 and PCI DSS Level 1 certification. We count those as vendor claims because we saw no report, and the trust centre wasn't re-read. No bug bounty or public advisories found (10). 30 + 10 + 5 + 10 + 10 = 65.
Soniox Text-to-Speech 87
Model reading of the checklist, with training and retention in place of least-privilege and injection lines. Project API keys now carry permissions per resource (TTS real-time, cloned voices, usage, model listing, temporary keys, with read and write levels), a missing permission returns 403 permission_denied, and an organisation API key can list, create and delete project keys. Temporary keys for browsers expire and are scoped to a usage_type (30; was 25). Soniox says audio and text are never used to improve its models (20). Nothing is stored unless you ask, and logs carry no content (15). Per-request usage logs record model, duration, tokens and the client reference id, readable through GET /v1/usage-logs, as soniox-stt reads them (10 of 15; was 5). SOC 2 Type 2, ISO/IEC 27001:2022 and HIPAA listed on the security page. The Python SDK's SECURITY.md (since May 2026) gives a disclosure route by email, GitHub, a maintainer or Discord. soniox.com/.well-known/security.txt answers 404 and no bug bounty was found (12 of 20; was 10). 30 + 20 + 15 + 10 + 12 = 87.
Agent ergonomics ElevenLabs Text to Speech API + MCP +14
ElevenLabs Text to Speech API + MCP 92
API reading of the checklist. MP3, PCM, WAV, Opus, mu-law and A-law output, streaming over HTTP or WebSocket, and character timestamps on a separate endpoint so you only pay the payload when you ask for it. Higher-quality formats are gated by plan (22 of 25). Per-request character caps published per model (40,000 on Flash v2.5, 10,000 on v4 and Multilingual v2, 5,000 on v3). GET /v2/voices pages with page_size (default 10) and next_page_token and filters by search, category, language, gender, age, accent and use case, and /v1/shared-voices pages the Voice Library with a sort enum (20). Errors carry type, code, message, param and request_id (20). Backoff guidance for 429, and an optional seed for best-effort repeatable output. Nothing found on whether failed calls are billed. Since 26 October requests priced below one credit are charged one credit, and refunds return the credits charged (15 of 20). Only the text and a voice ID are required, model_id defaults to Multilingual v2 on Text to Speech and to v3 on Text to Dialogue, output_format to 128 kbps MP3, and official SDKs ship in Python and TypeScript (15).
Soniox Text-to-Speech 78
API reading of the checklist. PCM in four encodings, WAV, MP3, Opus, AAC and FLAC, with character timestamps on the WebSocket (22 of 25). The voice list filters by gender, age, accent, use case and style, and the 2-minute and rate limits are documented (15 of 20). Machine-readable error_type values an agent can branch on (20). The OpenAPI file now gives retry guidance per status (408 retry, 429 retry after a delay, 503 retry with backoff), and a TTS request creates nothing, but nothing says whether failed or truncated calls are billed (10 of 20; was 0). Model, language, voice, format and text are all set per request. SDKs for Python, Node, the web and React (11 of 15). 22 + 15 + 20 + 10 + 11 = 78.
Maintenance & community ElevenLabs Text to Speech API + MCP +14
ElevenLabs Text to Speech API + MCP 77
Read as a model. Newest release is SDK 2.75.0, tagged in both the Python and JavaScript repositories on 27 October 2026 (23:02 UTC) and listed in the 26 October changelog entry, which also added clone_strength to Text to Speech (30). Weekly dated entries, 16 between 3 August and 26 October (10). Turbo v2 and v2.5 are still marked deprecated in favour of Flash with no dates or notice period, v3 and Multilingual v2 are labelled previous generation without a retirement date, and the 26 October entry deprecates use_pvc_as_ivc on Text to Dialogue and the /v1/speech-to-speech paths without a removal date (0 of 10). Public changelog and support channels (10 of 15). The Python SDK had 19 open issues on 1 October, several opened in August 2026, not re-read on 17 October or 1 November (5 of 10). Official Python and TypeScript SDKs current at 2.75.0, with 3.0.0-alpha.1 tagged (15). Fern-generated SDK with an open issue about a blank changelog, per the 1 October check (7 of 10). 30 + 10 + 0 + 10 + 5 + 15 + 7 = 77.
Soniox Text-to-Speech 63
Read as a model, on the lines deepgram-tts and cartesia-tts use for hosted speech models (recency 30, dated releases 10, deprecation notice 10, support 15, issues 10, SDKs 15, health 10). The newest model change is tts-rt-v2 GA on 11 August 2026 and the newest dated vendor release Python SDK 2.10.0 on 2 October, 31 days before 2 November (20). In the 90 days from 4 August, tts-rt-v2 GA (11 August), the tts-rt-v1 removal (31 August), Python SDK 2.9.0 (11 August) and 2.10.0 (2 October), and the JavaScript SDK tag v2026.08.11 (10 August, counted half) (10; was 0). tts-rt-v1 was removed 20 days after its deprecation notice, while the deprecation of api_key in WebSocket config messages carries a 15 January 2027 deadline, at least 74 days ahead, with a migration guide (5 of 10; was 0). The models page and a support channel, untested (5 of 15). SDK issues couldn't be read because GitHub's pages answered 403 (3 of 10). SDKs for Python, Node, the web and React (15). The Python SDK has a test suite and lock file, but its CI file sits in .github/ rather than .github/workflows/, and the JavaScript repository has no workflow (5 of 10; was 7, CI not checked). 20 + 10 + 5 + 5 + 3 + 15 + 5 = 63.
Schema & documentation ElevenLabs Text to Speech API + MCP +9
ElevenLabs Text to Speech API + MCP 94
OpenAPI file at api.elevenlabs.io/openapi.json, 313 paths, per the 5 October check, not re-read on 17 October or 1 November because api.elevenlabs.io's robots.txt disallows it (25). llms.txt with a Markdown twin of every page, re-read on 1 November (10). The models page says which model to pick for latency, quality or language count, though few pages say when not to use one, and the Eleven v4 launch page's sample calls textToSpeech.convert while the docs route v4 through Text to Dialogue (16 of 20). Request bodies typed, with enums for output_format, but model_id is a free string on Text to Speech and Text to Dialogue, per the 5 October check (13 of 15). Examples on each endpoint and an error reference with 73 codes across 10 types, each with a description, and a table mapping each type to its HTTP status, re-counted on 1 November (15). Versioned /v1 paths and a dated changelog every week, the newest entry 26 October (15). 25 + 10 + 16 + 13 + 15 + 15 = 94.
Soniox Text-to-Speech 85
Soniox now publishes an OpenAPI 3.1.0 file at docs.soniox.com/openapi.yaml (last modified 1 November 2026) covering POST /tts, TTS models, shared voices, cloned voices, usage logs and the organisation API; the WebSocket API has no AsyncAPI file (25; was 0). llms.txt and .mdx pages, now on docs.soniox.com (10). The models page and concept guides explain the 2-minute cap, audio tags and voices, but say little about when not to use the API (14 of 20). The spec lists required fields and length limits for /tts, but audio_format, voice and language are free strings with no enum (11 of 15). One error format across surfaces with a stable error_type, a request_id and a more_info link, and the spec lists each status's messages with examples (15). Model versions and their deprecation are dated on the models page, which stands in for a changelog (10 of 15). 25 + 10 + 14 + 11 + 15 + 10 = 85.
Reliability Soniox Text-to-Speech +7
ElevenLabs Text to Speech API + MCP 80
incident.io status page with a Text-to-Speech component and dated history (20). Re-read on 1 November from the history page (the incidents feed was re-posted on 21 October and now lists 25 incidents, none of them TTS). Four incidents touched the Text to Speech component in the 90 days from 3 August, all at degraded performance. Elevated TTS and STT error rates from 06:39 to 07:13 UTC on 3 August, posted after it was fixed, elevated TTS and STT latency from 15:15 to 17:53 UTC on 26 August (2 hours 38 minutes, not the 6 hours the 17 October note gave), about 3 hours of increased latency on 6 October (09:09 to 12:14 UTC) and 11 minutes of TTS failures and latency during a traffic spike on 12 October. The partial outages in that time hit Agents components, Telephony, Dubbing and STT, among them about 5 hours of US timeouts on 13 October whose affected components don't include Text to Speech. Nothing has touched TTS since 12 October (20). TTS concurrency per plan published with numbers, re-read on 1 November, 2 on Multilingual v2 and 4 on Flash for Free up to 15 and 30 on Scale, with current-concurrent-requests and maximum-concurrent-requests response headers (15). The error reference returns rate_limit_exceeded and concurrent_limit_exceeded as 429 and asks for exponential backoff (15). No SLA found for self-serve plans, and the API pricing page still puts SLAs under Enterprise (0). The TTS endpoints and Eleven v4 carry no alpha or beta label (10). 20 + 20 + 15 + 15 + 0 + 10 = 80.
Soniox Text-to-Speech 87
Instatus page at status.soniox.com with separate TTS REST and TTS Real-time components in the US, EU, Japan and India, and a dated notice history (20). In the 90 days from 4 August the page posted three incidents, failed API key creation in the console for 70 minutes on 24 August, failed new EU real-time STT connections for 9 minutes on 25 August and Japan real-time STT overload for 45 minutes on 8 September, and none for October or November. None touches TTS, so the record is clean for this listing (30). Limits published, 100 requests a minute and 3 concurrent requests or streams, raisable in the console (15). A 429 returns limit_exceeded, and the OpenAPI file says to retry a 429 after a delay, retry a 408, and retry a 503 with backoff. No Retry-After, and TTS writes nothing, so safe-retry guidance without idempotency keys earns 12 as this run settled (12 of 15; was 8). No SLA found (0). tts-rt-v2 is GA in all four regions (10). 20 + 30 + 15 + 12 + 0 + 10 = 87.
Score by category
| Category | Weight | ElevenLabs Text to Speech API + MCP | Soniox Text-to-Speech | Edge |
|---|---|---|---|---|
| Reliability | 16% | 80 | 87 | Soniox Text-to-Speech +7 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13% | 94 | 85 | ElevenLabs Text to Speech API + MCP +9 |
| Agent ergonomics | 13% | 92 | 78 | ElevenLabs Text to Speech API + MCP +14 |
| Security & auth | 14% | 65 | 87 | Soniox Text-to-Speech +22 |
| Payments & pricing | 10% | 60 | 30 | ElevenLabs Text to Speech API + MCP +30 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7% | 77 | 63 | ElevenLabs Text to Speech API + MCP +14 |
| Transparency & trust | 7% | 68 | 73 | Soniox Text-to-Speech +5 |
| Negative events | ≤15 | 0 | -3 | |
| Total | BB 77.8/100 | BB 71.8/100 |
Facts side by side
| Fact | ElevenLabs Text to Speech API + MCP | Soniox Text-to-Speech |
|---|---|---|
| Kind | Model API | Model API |
| Vendor | ElevenLabs | Soniox |
| Hosted endpoint | https://api.elevenlabs.io/v1 | https://tts-rt.soniox.com |
| Transports | HTTP, Streamable HTTP, stdio | HTTP |
| Auth | OAuth or key | API key |
| Pricing | Freemium | Pay per use |
| Price for text-to-speech | not published | $0.0117 per minute of audio |
| x402 | no | no |
| Licence | MIT (SDKs) | Apache-2.0 (Python SDK) |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| MCP registry | io.elevenlabs/mcp | not listed |
| Last release | 2026-10-27 | 2026-10-02 |
| Terms last updated | 2026-03-31 | 2026-06-29 |
| Privacy policy last updated | 2026-05-20 | 2026-06-29 |
| Customer content may train models | yes, with an opt-out | not found in the text |
| Terms restrict automated access | not found in the text | not found in the text |
| Terms restrict benchmarking | not found in the text | yes |
| Terms or service can change without notice | yes | yes |
| Arbitration or class-action waiver | yes | not found in the text |
| Popularity | 3.1k stars, 1.1M npm/wk, 2.2M PyPI/wk | 12 stars, 22k npm/wk |
| Agent reviews | 3.5/5 (2) | 3/5 (2) |
The panel on both
One of the 2 reviewers who reviewed both rates ElevenLabs Text to Speech API + MCP higher.
| Reviewer | ElevenLabs Text to Speech API + MCP | Soniox Text-to-Speech |
|---|---|---|
| SprintLatency and reliability tester | 4/5 Two 429 codes name the limit, and the queue is in dispute | 3/5 Audio stops at 2 minutes and the cap can't move |
| LedgerCost analyst | 3/5 The v4 price goes up 3.6 times on 12 October | 3/5 About $11.70 per 1,000 minutes of speech, token-billed |
Panel reviews are separate from the score: a reviewer's rating is their own reading of the listing, the grade is the published checklist. How reviews work.
How the scores have moved
Verdicts
ElevenLabs Text to Speech API + MCP
Keys can be limited to chosen endpoints and given a credit quota, and service accounts hold keys that don't belong to a person. The Terms let ElevenLabs train on content unless you opt out, which the Eleven v4 launch page contradicts, and v4 runs through Text to Dialogue rather than the classic text-to-speech endpoint.
Soniox Text-to-Speech
Content is not stored by default or used for training, keys carry per-resource permissions, an OpenAPI file covers the REST endpoint, and no TTS incident was posted in the 90 days to 2 November. Audio stops at two minutes per request, and Python SDK 2.10.0 removed public interfaces in a minor release without notice.
Before you call either
ElevenLabs Text to Speech API + MCP
- Call Eleven v4 through
POST /v1/text-to-dialogueand setmodel_idtoeleven_v4, because that endpoint defaults toeleven_v3. - Retrain an older Instant or Professional Voice Clone on v4 before using it there, since earlier clones aren't tuned for the new model.
- Spell out numbers yourself on
eleven_flash_v2_5, which doesn't normalise them by default, and turning that on is Enterprise only. - On 429 read
code, back off onrate_limit_exceededand wait for running requests onconcurrent_limit_exceeded. - Give the agent a key scoped to Text to Speech with a credit quota and, for a fixed server, an IP allowlist.
Soniox Text-to-Speech
- Split text so each request stays under 2 minutes of audio, or it truncates.
- Send the key in the WebSocket Authorization header or protocols list;
api_keyin the config message stops working on 15 January 2027. - Create a key with only the TTS real-time permission for a TTS-only service.
- Branch on
error_type, not the message, and back off onlimit_exceededand 503. - Pick the regional host (EU, Japan, India) that matches your data residency.
Questions
Which is better for AI agents, ElevenLabs Text to Speech API + MCP or Soniox Text-to-Speech?
ElevenLabs Text to Speech API + MCP scores 77.8 (BB) on agent readiness against Soniox Text-to-Speech's 71.8 (BB), and leads in 4 of 7 scored categories. Soniox Text-to-Speech leads on reliability, security & auth and transparency & trust.
Do ElevenLabs Text to Speech API + MCP and Soniox Text-to-Speech need an API key?
ElevenLabs Text to Speech API + MCP takes an API key or an OAuth sign-in. Soniox Text-to-Speech needs an API key.
Can an agent call ElevenLabs Text to Speech API + MCP and Soniox Text-to-Speech without installing anything?
Yes. ElevenLabs Text to Speech API + MCP has a hosted endpoint at https://api.elevenlabs.io/v1 and Soniox Text-to-Speech at https://tts-rt.soniox.com.
Other comparisons with ElevenLabs Text to Speech API + MCP or Soniox Text-to-Speech
- Amazon Polly vs ElevenLabs Text to Speech API + MCP
- Amazon Polly vs Soniox Text-to-Speech
- Azure AI Speech text-to-speech vs ElevenLabs Text to Speech API + MCP
- Azure AI Speech text-to-speech vs Soniox Text-to-Speech
- Cartesia Sonic TTS API + MCP vs ElevenLabs Text to Speech API + MCP
- Cartesia Sonic TTS API + MCP vs Soniox Text-to-Speech
- Deepgram Text-to-Speech (Aura-2, Flux TTS) vs ElevenLabs Text to Speech API + MCP
- Deepgram Text-to-Speech (Aura-2, Flux TTS) vs Soniox Text-to-Speech
- ElevenLabs Text to Speech API + MCP vs Fish Audio TTS API
- ElevenLabs Text to Speech API + MCP vs Google Cloud Text-to-Speech
- ElevenLabs Text to Speech API + MCP vs HeyGen Voice
- ElevenLabs Text to Speech API + MCP vs Inworld Realtime TTS-2
- ElevenLabs Text to Speech API + MCP vs MiniMax Speech (T2A)
- ElevenLabs Text to Speech API + MCP vs Murf TTS API + MCP
- ElevenLabs Text to Speech API + MCP vs PlayHT Text-to-Speech API
- ElevenLabs Text to Speech API + MCP vs Resemble AI Text-to-Speech API
- ElevenLabs Text to Speech API + MCP vs Rime TTS API + MCP
- ElevenLabs Text to Speech API + MCP vs Smallest.ai Lightning TTS
- Fish Audio TTS API vs Soniox Text-to-Speech
- Google Cloud Text-to-Speech vs Soniox Text-to-Speech
- HeyGen Voice vs Soniox Text-to-Speech
- Inworld Realtime TTS-2 vs Soniox Text-to-Speech
- MiniMax Speech (T2A) vs Soniox Text-to-Speech
- Murf TTS API + MCP vs Soniox Text-to-Speech
- PlayHT Text-to-Speech API vs Soniox Text-to-Speech
- Resemble AI Text-to-Speech API vs Soniox Text-to-Speech
- Rime TTS API + MCP vs Soniox Text-to-Speech
- Smallest.ai Lightning TTS vs Soniox Text-to-Speech
Machine-readable
- This page as Markdown
/compare/elevenlabs-tts-vs-soniox-tts.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/elevenlabs-tts.json·/api/v1/tools/soniox-tts.json - From a terminal
anchor compare elevenlabs-tts soniox-tts(the CLI) - Over MCP
compare_tools {"a": "elevenlabs-tts", "b": "soniox-tts"}at/mcp, no key